mradermacher
commited on
Commit
•
609f2f6
1
Parent(s):
c01eb4e
auto-patch README.md
Browse files
README.md
CHANGED
@@ -41,7 +41,18 @@ more details, including on how to concatenate multi-part files.
|
|
41 |
|
42 |
| Link | Type | Size/GB | Notes |
|
43 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
44 |
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
47 |
types (lower is better):
|
|
|
41 |
|
42 |
| Link | Type | Size/GB | Notes |
|
43 |
|:-----|:-----|--------:|:------|
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q2_K.gguf) | Q2_K | 1.5 | |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q3_K_S.gguf) | Q3_K_S | 1.8 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.IQ4_XS.gguf) | IQ4_XS | 2.2 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q3_K_L.gguf) | Q3_K_L | 2.2 | |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended |
|
50 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended |
|
51 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q5_K_S.gguf) | Q5_K_S | 2.7 | |
|
52 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q5_K_M.gguf) | Q5_K_M | 2.9 | |
|
53 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q6_K.gguf) | Q6_K | 3.2 | very good quality |
|
54 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality |
|
55 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.2-phi3-4b-GGUF/resolve/main/calme-2.2-phi3-4b.f16.gguf) | f16 | 7.7 | 16 bpw, overkill |
|
56 |
|
57 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
58 |
types (lower is better):
|