mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -103,7 +103,27 @@ more details, including on how to concatenate multi-part files.
|
|
103 |
|
104 |
| Link | Type | Size/GB | Notes |
|
105 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q2_K.gguf) | i1-Q2_K | 45.3 | IQ3_XXS probably better |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
107 |
|
108 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
109 |
types (lower is better):
|
|
|
103 |
|
104 |
| Link | Type | Size/GB | Notes |
|
105 |
|:-----|:-----|--------:|:------|
|
106 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ1_S.gguf) | i1-IQ1_S | 26.1 | for the desperate |
|
107 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ1_M.gguf) | i1-IQ1_M | 28.5 | mostly desperate |
|
108 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 32.5 | |
|
109 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ2_XS.gguf) | i1-IQ2_XS | 36.2 | |
|
110 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ2_S.gguf) | i1-IQ2_S | 38.5 | |
|
111 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ2_M.gguf) | i1-IQ2_M | 41.7 | |
|
112 |
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q2_K.gguf) | i1-Q2_K | 45.3 | IQ3_XXS probably better |
|
113 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 47.1 | lower quality |
|
114 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 50.2 | |
|
115 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 52.9 | IQ3_XS probably better |
|
116 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 53.1 | beats Q3_K* |
|
117 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 55.4 | |
|
118 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 59.2 | IQ3_S probably better |
|
119 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 64.7 | IQ3_M probably better |
|
120 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 65.5 | |
|
121 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 69.4 | fast, low quality |
|
122 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 69.7 | optimal size/speed/quality |
|
123 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 73.3 | fast, recommended |
|
124 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 84.5 | |
|
125 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 86.6 | |
|
126 |
+
| [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2411-i1-GGUF/resolve/main/Mistral-Large-Instruct-2411.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 100.7 | practically like static Q6_K |
|
127 |
|
128 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
129 |
types (lower is better):
|