auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -46,7 +46,15 @@ more details, including on how to concatenate multi-part files.
|
|
| 46 |
| Link | Type | Size/GB | Notes |
|
| 47 |
|:-----|:-----|--------:|:------|
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q2_K.gguf) | Q2_K | 29.9 | |
|
|
|
|
|
|
|
|
|
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 52 |
types (lower is better):
|
|
|
|
| 46 |
| Link | Type | Size/GB | Notes |
|
| 47 |
|:-----|:-----|--------:|:------|
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q2_K.gguf) | Q2_K | 29.9 | |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q3_K_S.gguf) | Q3_K_S | 34.6 | |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q3_K_M.gguf) | Q3_K_M | 37.8 | lower quality |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q3_K_L.gguf) | Q3_K_L | 39.6 | |
|
| 52 |
| [GGUF](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
|
| 53 |
+
| [GGUF](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q4_K_M.gguf) | Q4_K_M | 47.5 | fast, recommended |
|
| 54 |
+
| [PART 1](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q5_K_S.gguf.part2of2) | Q5_K_S | 51.5 | |
|
| 55 |
+
| [PART 1](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 | |
|
| 56 |
+
| [PART 1](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
|
| 57 |
+
| [PART 1](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/SimpleChat-72B-V4-Apache2.0-GGUF/resolve/main/SimpleChat-72B-V4-Apache2.0.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
|
| 58 |
|
| 59 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 60 |
types (lower is better):
|