mradermacher
commited on
Commit
•
1e1bae3
1
Parent(s):
c920001
auto-patch README.md
Browse files
README.md
CHANGED
@@ -28,17 +28,26 @@ more details, including on how to concatenate multi-part files.
|
|
28 |
|
29 |
| Link | Type | Size/GB | Notes |
|
30 |
|:-----|:-----|--------:|:------|
|
|
|
31 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | |
|
|
|
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | |
|
34 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 1.7 | IQ3_XXS probably better |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.7 | lower quality |
|
|
|
|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 2.0 | |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.1 | IQ3_S probably better |
|
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.3 | |
|
|
|
40 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.4 | optimal size/speed/quality |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended |
|
|
|
|
|
42 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q6_K.gguf) | i1-Q6_K | 3.3 | practically like static Q6_K |
|
43 |
|
44 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
28 |
|
29 |
| Link | Type | Size/GB | Notes |
|
30 |
|:-----|:-----|--------:|:------|
|
31 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | |
|
34 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.4 | |
|
35 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 1.7 | IQ3_XXS probably better |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.7 | lower quality |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 2.0 | |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.1 | IQ3_S probably better |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.3 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 2.4 | fast, low quality |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.4 | optimal size/speed/quality |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | |
|
50 |
+
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.9 | |
|
51 |
| [GGUF](https://huggingface.co/mradermacher/J.O.S.I.E.-x-Qwen1.5-4B-Chat-i1-GGUF/resolve/main/J.O.S.I.E.-x-Qwen1.5-4B-Chat.i1-Q6_K.gguf) | i1-Q6_K | 3.3 | practically like static Q6_K |
|
52 |
|
53 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|