Commit
•
6693a8e
1
Parent(s):
48a163c
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -32,8 +32,20 @@ more details, including on how to concatenate multi-part files.
|
|
| 32 |
| Link | Type | Size/GB | Notes |
|
| 33 |
|:-----|:-----|--------:|:------|
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q2_K.gguf) | Q2_K | 3.4 | |
|
|
|
|
|
|
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.IQ3_S.gguf) | IQ3_S | 4.0 | beats Q3_K* |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 5.0 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 39 |
types (lower is better):
|
|
|
|
| 32 |
| Link | Type | Size/GB | Notes |
|
| 33 |
|:-----|:-----|--------:|:------|
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q2_K.gguf) | Q2_K | 3.4 | |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.IQ3_XS.gguf) | IQ3_XS | 3.8 | |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.9 | |
|
| 37 |
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.IQ3_S.gguf) | IQ3_S | 4.0 | beats Q3_K* |
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.IQ3_M.gguf) | IQ3_M | 4.1 | |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.3 | lower quality |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.6 | |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.8 | |
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 5.0 | fast, recommended |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.2 | fast, recommended |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 6.0 | |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 6.1 | |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q6_K.gguf) | Q6_K | 7.0 | very good quality |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.Q8_0.gguf) | Q8_0 | 9.0 | fast, best quality |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Instruct-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Instruct.f16.gguf) | f16 | 16.9 | 16 bpw, overkill |
|
| 49 |
|
| 50 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 51 |
types (lower is better):
|