auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ quantized_by: mradermacher
|
|
| 16 |
static quants of https://huggingface.co/mistralai/Mathstral-7B-v0.1
|
| 17 |
|
| 18 |
<!-- provided-files -->
|
| 19 |
-
weighted/imatrix quants
|
| 20 |
## Usage
|
| 21 |
|
| 22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
@@ -29,22 +29,22 @@ more details, including on how to concatenate multi-part files.
|
|
| 29 |
|
| 30 |
| Link | Type | Size/GB | Notes |
|
| 31 |
|:-----|:-----|--------:|:------|
|
| 32 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 33 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 34 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 35 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 36 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 37 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 38 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 39 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 40 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 41 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 42 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 43 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 44 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 45 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 46 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 47 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 48 |
|
| 49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 50 |
types (lower is better):
|
|
|
|
| 16 |
static quants of https://huggingface.co/mistralai/Mathstral-7B-v0.1
|
| 17 |
|
| 18 |
<!-- provided-files -->
|
| 19 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mathstral-7B-v0.1-i1-GGUF
|
| 20 |
## Usage
|
| 21 |
|
| 22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 29 |
|
| 30 |
| Link | Type | Size/GB | Notes |
|
| 31 |
|:-----|:-----|--------:|:------|
|
| 32 |
+
| [GGUF](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
|
| 33 |
+
| [GGUF](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
|
| 34 |
+
| [GGUF](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.IQ3_M.gguf) | IQ3_M | 3.4 | |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality |
|
| 36 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q2_K.gguf) | Q2_K | 5.5 | |
|
| 37 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q3_K_S.gguf) | Q3_K_S | 6.4 | |
|
| 38 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q3_K_M.gguf) | Q3_K_M | 7.1 | lower quality |
|
| 39 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q3_K_L.gguf) | Q3_K_L | 7.8 | |
|
| 40 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.IQ4_XS.gguf) | IQ4_XS | 8.0 | |
|
| 41 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q4_K_S.gguf) | Q4_K_S | 8.4 | fast, recommended |
|
| 42 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q4_K_M.gguf) | Q4_K_M | 8.8 | fast, recommended |
|
| 43 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q5_K_S.gguf) | Q5_K_S | 10.1 | |
|
| 44 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q5_K_M.gguf) | Q5_K_M | 10.4 | |
|
| 45 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q6_K.gguf) | Q6_K | 12.0 | very good quality |
|
| 46 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.Q8_0.gguf) | Q8_0 | 15.5 | fast, best quality |
|
| 47 |
+
| [PART 1](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/Mathstral-7B-v0.1.f16.gguf) [PART 2](https://huggingface.co/mradermacher/Mathstral-7B-v0.1-GGUF/resolve/main/mathstral-7B-v0.1.f16.gguf) | f16 | 29.1 | 16 bpw, overkill |
|
| 48 |
|
| 49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 50 |
types (lower is better):
|