Hugging Face's logo

bartowski
/
c4ai-command-r-plus-GGUF

Text Generation
Transformers
GGUF
Inference Endpoints
Model card Files Community
2
bartowski commited on
Commit
7070156
•
1 Parent(s): 1abf47e

Llamacpp quants

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +53 -0
  2. README.md +75 -0
  3. c4ai-command-r-plus-IQ3_M.gguf +3 -0
  4. c4ai-command-r-plus-IQ3_S.gguf +3 -0
  5. c4ai-command-r-plus-IQ3_XS.gguf +3 -0
  6. c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00001-of-00006.gguf +3 -0
  7. c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00002-of-00006.gguf +3 -0
  8. c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00003-of-00006.gguf +3 -0
  9. c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00004-of-00006.gguf +3 -0
  10. c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00005-of-00006.gguf +3 -0
  11. c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00006-of-00006.gguf +3 -0
  12. c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00001-of-00006.gguf +3 -0
  13. c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00002-of-00006.gguf +3 -0
  14. c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00003-of-00006.gguf +3 -0
  15. c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00004-of-00006.gguf +3 -0
  16. c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00005-of-00006.gguf +3 -0
  17. c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00006-of-00006.gguf +3 -0
  18. c4ai-command-r-plus-Q2_K.gguf +3 -0
  19. c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00001-of-00006.gguf +3 -0
  20. c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00002-of-00006.gguf +3 -0
  21. c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00003-of-00006.gguf +3 -0
  22. c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00004-of-00006.gguf +3 -0
  23. c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00005-of-00006.gguf +3 -0
  24. c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00006-of-00006.gguf +3 -0
  25. c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00001-of-00006.gguf +3 -0
  26. c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00002-of-00006.gguf +3 -0
  27. c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00003-of-00006.gguf +3 -0
  28. c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00004-of-00006.gguf +3 -0
  29. c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00005-of-00006.gguf +3 -0
  30. c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00006-of-00006.gguf +3 -0
  31. c4ai-command-r-plus-Q3_K_S.gguf +3 -0
  32. c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00001-of-00006.gguf +3 -0
  33. c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00002-of-00006.gguf +3 -0
  34. c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00003-of-00006.gguf +3 -0
  35. c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00004-of-00006.gguf +3 -0
  36. c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00005-of-00006.gguf +3 -0
  37. c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00006-of-00006.gguf +3 -0
  38. c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00001-of-00006.gguf +3 -0
  39. c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00002-of-00006.gguf +3 -0
  40. c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00003-of-00006.gguf +3 -0
  41. c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00004-of-00006.gguf +3 -0
  42. c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00005-of-00006.gguf +3 -0
  43. c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00006-of-00006.gguf +3 -0
  44. c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00001-of-00006.gguf +3 -0
  45. c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00002-of-00006.gguf +3 -0
  46. c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00003-of-00006.gguf +3 -0
  47. c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00004-of-00006.gguf +3 -0
  48. c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00005-of-00006.gguf +3 -0
  49. c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00006-of-00006.gguf +3 -0
  50. c4ai-command-r-plus-Q5_K_S.gguf/c4ai-command-r-plus-Q5_K_S-00001-of-00006.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,56 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ c4ai-command-r-plus-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ c4ai-command-r-plus-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ c4ai-command-r-plus-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
39
+ c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
40
+ c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
41
+ c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
42
+ c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
43
+ c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
44
+ c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
45
+ c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
46
+ c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
47
+ c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
48
+ c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
49
+ c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
50
+ c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
51
+ c4ai-command-r-plus-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
52
+ c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
53
+ c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
54
+ c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
55
+ c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
56
+ c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
57
+ c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
58
+ c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
59
+ c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
60
+ c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
61
+ c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
62
+ c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
63
+ c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
64
+ c4ai-command-r-plus-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
65
+ c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
66
+ c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
67
+ c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
68
+ c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
69
+ c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
70
+ c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
71
+ c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
72
+ c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
73
+ c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
74
+ c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
75
+ c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
76
+ c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
77
+ c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
78
+ c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
79
+ c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
80
+ c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
81
+ c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
82
+ c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
83
+ c4ai-command-r-plus-Q5_K_S.gguf/c4ai-command-r-plus-Q5_K_S-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
84
+ c4ai-command-r-plus-Q5_K_S.gguf/c4ai-command-r-plus-Q5_K_S-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
85
+ c4ai-command-r-plus-Q5_K_S.gguf/c4ai-command-r-plus-Q5_K_S-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
86
+ c4ai-command-r-plus-Q5_K_S.gguf/c4ai-command-r-plus-Q5_K_S-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
87
+ c4ai-command-r-plus-Q5_K_S.gguf/c4ai-command-r-plus-Q5_K_S-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
88
+ c4ai-command-r-plus-Q5_K_S.gguf/c4ai-command-r-plus-Q5_K_S-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ library_name: transformers
4
+ language:
5
+ - en
6
+ - fr
7
+ - de
8
+ - es
9
+ - it
10
+ - pt
11
+ - ja
12
+ - ko
13
+ - zh
14
+ - ar
15
+ quantized_by: bartowski
16
+ pipeline_tag: text-generation
17
+ ---
18
+
19
+ ## Llamacpp Quantizations of c4ai-command-r-plus
20
+
21
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2636">b2636</a> for quantization.
22
+
23
+ Original model: https://huggingface.co/CohereForAI/c4ai-command-r-plus
24
+
25
+ ## Prompt format
26
+
27
+ ```
28
+ <BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{system_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
29
+ ```
30
+
31
+ ## Download a file (not the whole branch) from below:
32
+
33
+ | Filename | Quant type | File Size | Description |
34
+ | -------- | ---------- | --------- | ----------- |
35
+ | [c4ai-command-r-plus-Q8_0.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF//main/c4ai-command-r-plus-Q8_0.gguf) | Q8_0 | | Extremely high quality, generally unneeded but max available quant. |
36
+ | [c4ai-command-r-plus-Q6_K.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF//main/c4ai-command-r-plus-Q6_K.gguf) | Q6_K | | Very high quality, near perfect, *recommended*. |
37
+ | [c4ai-command-r-plus-Q5_K_M.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/tree/main/c4ai-command-r-plus-Q5_K_M.gguf) | Q5_K_M | 73.62GB | High quality, *recommended*. |
38
+ | [c4ai-command-r-plus-Q5_K_S.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/tree/main/c4ai-command-r-plus-Q5_K_S.gguf) | Q5_K_S | 71.80GB | High quality, *recommended*. |
39
+ | [c4ai-command-r-plus-Q4_K_M.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/tree/main/c4ai-command-r-plus-Q4_K_M.gguf) | Q4_K_M | 62.75GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
40
+ | [c4ai-command-r-plus-Q4_K_S.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/tree/main/c4ai-command-r-plus-Q4_K_S.gguf) | Q4_K_S | 59.64GB | Slightly lower quality with more space savings, *recommended*. |
41
+ | [c4ai-command-r-plus-IQ4_NL.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/tree/main/c4ai-command-r-plus-IQ4_NL.gguf) | IQ4_NL | 59.73GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
42
+ | [c4ai-command-r-plus-IQ4_XS.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/tree/main/c4ai-command-r-plus-IQ4_XS.gguf) | IQ4_XS | 56.72GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
43
+ | [c4ai-command-r-plus-Q3_K_L.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/tree/main/c4ai-command-r-plus-Q3_K_L.gguf) | Q3_K_L | 55.40GB | Lower quality but usable, good for low RAM availability. |
44
+ | [c4ai-command-r-plus-Q3_K_M.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/tree/main/c4ai-command-r-plus-Q3_K_M.gguf) | Q3_K_M | 50.98GB | Even lower quality. |
45
+ | [c4ai-command-r-plus-IQ3_M.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/blob/main/c4ai-command-r-plus-IQ3_M.gguf) | IQ3_M | 47.68GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
46
+ | [c4ai-command-r-plus-IQ3_S.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/blob/main/c4ai-command-r-plus-IQ3_S.gguf) | IQ3_S | 45.95GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
47
+ | [c4ai-command-r-plus-Q3_K_S.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/blob/main/c4ai-command-r-plus-Q3_K_S.gguf) | Q3_K_S | 45.85GB | Low quality, not recommended. |
48
+ | [c4ai-command-r-plus-IQ3_XS.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/blob/main/c4ai-command-r-plus-IQ3_XS.gguf) | IQ3_XS | 43.59GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
49
+ | [c4ai-command-r-plus-Q2_K.gguf](https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF/blob/main/c4ai-command-r-plus-Q2_K.gguf) | Q2_K | 39.49GB | Very low quality but surprisingly usable. |
50
+
51
+ ## Which file should I choose?
52
+
53
+ A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
54
+
55
+ The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
56
+
57
+ If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
58
+
59
+ If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
60
+
61
+ Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
62
+
63
+ If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
64
+
65
+ If you want to get more into the weeds, you can check out this extremely useful feature chart:
66
+
67
+ [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
68
+
69
+ But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
70
+
71
+ These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
72
+
73
+ The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
74
+
75
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
c4ai-command-r-plus-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:113ad0f9a1ce36b1afed6f778219f540bb1aa870e50d85b10eeec06477d2dcb8
3
+ size 47683347712
c4ai-command-r-plus-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca41f6369d7d4c6f7babc275e891b67a3ded3219245e63473e726d9141a6ab7e
3
+ size 45958702336
c4ai-command-r-plus-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0151568cae164035502af55cc01bed576d2ed3bd45edd5fc871b2b2b386f7e6c
3
+ size 43599406336
c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d26532dfb7af3306dfe5c840c5d4379cafec99c497530dbd9309e46705ca123
3
+ size 14351415840
c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d348a8cf312ee35a01e414cbd8be34d087d31c92099d0e9320023bf4eea02d11
3
+ size 11141099328
c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef72516dc5ad6e762869a976997c97948c152765e66a499d54f13c7b42888d33
3
+ size 11664908064
c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306b8bedb147abe68c4fd84a6e8d4b972470510045f210d17d1f2e5165d74561
3
+ size 11056168768
c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4e53acb9b737899df3a1c8a3508e76f9a1e6cb5c2452c071d78c068cf6a407
3
+ size 11514699552
c4ai-command-r-plus-IQ4_NL.gguf/c4ai-command-r-plus-IQ4_NL-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989e6989c27d0dca650bb65660454a01a10a2be11831e401d8e54b50394ee545
3
+ size 8700128
c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91656b99e5cf65f520116d3e38ea1415f13ce205c9849fbc1031b6fe831d1a17
3
+ size 13830797856
c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5544644f9136b8ffe44996c83b8c9437506c3d607e513173b2287cd6b33df09f
3
+ size 10528468800
c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74bccb709113f9f6fc57610805922ff979804738e0ee71dba5641d0381eb8882
3
+ size 11023179552
c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3fd02edc68f30ef9e706ba83847b2f5e1e20723df6728d588460696eb392d2f
3
+ size 10448256832
c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fef0ef67eaae7f401ed7c9db56fc806c9655ca456dbdd35b9feb9998042d5e
3
+ size 10880835360
c4ai-command-r-plus-IQ4_XS.gguf/c4ai-command-r-plus-IQ4_XS-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989e6989c27d0dca650bb65660454a01a10a2be11831e401d8e54b50394ee545
3
+ size 8700128
c4ai-command-r-plus-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e139a57872a72096c05b043b1ec6c2f08451da7df0d84d45168708667b98f5
3
+ size 39497377024
c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38b3f388118da6d4f5f8503b11076311a784b1dfc19ef91eb2e3e7130befbbb
3
+ size 13141195296
c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cacdf66b6c31345b1663f187bab4bc9d140bb0fef7f5fcf18616ec366767e79
3
+ size 10367053632
c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd666ad601d60d630eafc4e93741fa9616ca7059072bddf77d394a2786f5d3e2
3
+ size 10903445280
c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcf9b65b7c616bf385c1546a5172872b9e4dfb6f01bb21414a67c4bf4cc76b4
3
+ size 10263248704
c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fe6a00df48b82ecc41ebf3aea788fe12003e0f8ef003ddb8082c535aec7e15
3
+ size 10718535456
c4ai-command-r-plus-Q3_K_L.gguf/c4ai-command-r-plus-Q3_K_L-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989e6989c27d0dca650bb65660454a01a10a2be11831e401d8e54b50394ee545
3
+ size 8700128
c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:361bc3613b10c191e8465167dcb5500a992026e78b7ec8e9b5837d663272c2e7
3
+ size 12431833632
c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8970e98145f9806e04558f95fa3c8e1fb974ca5079170b76c76b5a88eb9a4c3a
3
+ size 9459511104
c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:093df41f06842d61b5ced56706d67be30196255e38bd40b27f0a7570c0036a08
3
+ size 9929842464
c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d870dfc53e3f83ce68f5775c6bdf619a35a298fc0c849bdfd9066dbc44b214
3
+ size 9374580544
c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f689eeeeea49f24263f5072260354e5609c4ba67e90bb1f0c7a3ea732cc5d6b
3
+ size 9779535648
c4ai-command-r-plus-Q3_K_M.gguf/c4ai-command-r-plus-Q3_K_M-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1a2b248a941b29a0d235054778ffeaa9ebf0ac893cc3270bc578b587fa995b
3
+ size 7127264
c4ai-command-r-plus-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4460761275ce9f709c738aacecdb39970d780f9260e948b508c5100fc4e19d
3
+ size 45851747584
c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f787a81559e76de58e7fffe6803ff7adbb4b0ee24bd52198e36205ca6ff22ae0
3
+ size 14909979168
c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a484307883e419ea7f39f41c170b3566d66157e7023d73a735492ae55225fb
3
+ size 11561840448
c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944304189cf77ac16cedc9895fc097ccbf5d2d7c1cc38c0d0c851ee6a0e9430d
3
+ size 12195946272
c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82a2640094bd1fabc9f2724c808ad072af88934de129aeedb0223d644d9bf5c
3
+ size 11476909888
c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa03984e911ee98097cfcacb0e0b91d0e87d1de0135838707b36cbc4f79b7acc
3
+ size 12595552032
c4ai-command-r-plus-Q4_K_M.gguf/c4ai-command-r-plus-Q4_K_M-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c6f47ec44f4154d20b18a1d9b0385cca403d92e0fad84714e412638e52199f3
3
+ size 10371296
c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89d404a25354900632925f35eedf749c52281ba4f315f38af6fd95b6a7d25fc
3
+ size 14338832928
c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:393be69cb36e73a5786695f12a1d7be113fd65341c997fbc4692ed5a0cc76d9a
3
+ size 11120652096
c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a6b0042549659a6347120b50bd71f0b5becc7aaa1fa7c2d0f848556aec6a56
3
+ size 11644460832
c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6efb6289ad8d2295aa61fa63bd3cfab53ffaabd4d9fcb9c930221b8e064f2f
3
+ size 11035721536
c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439dfc8f4bf824d5405fbcb43818fea67aad8e0331559044f02f5db0e90603b6
3
+ size 11495825184
c4ai-command-r-plus-Q4_K_S.gguf/c4ai-command-r-plus-Q4_K_S-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1a2b248a941b29a0d235054778ffeaa9ebf0ac893cc3270bc578b587fa995b
3
+ size 7127264
c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1a2a82e15d01d2f07d4b40c6c1e9efeb4a2cf83c3589d37193575091afbb97
3
+ size 16945265184
c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf72dfbb315a375e6930d4f5f363c42d4ab70e36c5780bec3d03f47c1c05624
3
+ size 13818900288
c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ffbc577f086da18b0fe1e7594eb1cd9aeab6595aed9500229cb9038d5fff8f
3
+ size 14515920672
c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88508c31b78cf518f5b4e2dfe74eb99a99bfb8c4deeae147512416f1e419266
3
+ size 13715095360
c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c910f4ef795a120ab35a20a4ef7933dfff49b8f9fcc0a0275987f94cff2440
3
+ size 14616682272
c4ai-command-r-plus-Q5_K_M.gguf/c4ai-command-r-plus-Q5_K_M-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c6f47ec44f4154d20b18a1d9b0385cca403d92e0fad84714e412638e52199f3
3
+ size 10371296
c4ai-command-r-plus-Q5_K_S.gguf/c4ai-command-r-plus-Q5_K_S-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a22e78d71eb83427c34639670516250cf6ea789b598b02dcb33f64bb6b99316
3
+ size 16433887776