mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -34,7 +34,18 @@ more details, including on how to concatenate multi-part files.
|
|
34 |
|
35 |
| Link | Type | Size/GB | Notes |
|
36 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.f16.gguf) | f16 | 21.6 | 16 bpw, overkill |
|
39 |
|
40 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
34 |
|
35 |
| Link | Type | Size/GB | Notes |
|
36 |
|:-----|:-----|--------:|:------|
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q2_K.gguf) | Q2_K | 4.1 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q3_K_S.gguf) | Q3_K_S | 4.8 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.IQ4_XS.gguf) | IQ4_XS | 5.9 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q4_0_4_4.gguf) | Q4_0_4_4 | 6.2 | fast on arm, low quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q5_K_S.gguf) | Q5_K_S | 7.5 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q5_K_M.gguf) | Q5_K_M | 7.7 | |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q6_K.gguf) | Q6_K | 8.9 | very good quality |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q8_0.gguf) | Q8_0 | 11.5 | fast, best quality |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.f16.gguf) | f16 | 21.6 | 16 bpw, overkill |
|
50 |
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|