mradermacher
/

Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF

Transformers

GGUF

English

Inference Endpoints

conversational

Model card Files Files and versions Community

mradermacher commited on Jan 19

Commit

9efebc9

verified ·

1 Parent(s): 85a7cb6

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -33,10 +33,14 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q3_K_S.gguf) | Q3_K_S | 3.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q3_K_L.gguf) | Q3_K_L | 3.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):

 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q3_K_S.gguf) | Q3_K_S | 3.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q3_K_L.gguf) | Q3_K_L | 3.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.IQ4_XS.gguf) | IQ4_XS | 4.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q5_K_S.gguf) | Q5_K_S | 5.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q5_K_M.gguf) | Q5_K_M | 5.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-open-instruct-ro-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-open-instruct-ro.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):