andrijdavid
/

Voxtral-Mini-3B-2507-GGUF

Automatic Speech Recognition

Model card Files Files and versions

andrijdavid commited on Jun 14

Commit

7a4e86d

·

verified ·

1 Parent(s): be7c2db

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ language:
   - it
 ---
-# Voxtral-Mini-3B-2507 — GGUF
 GGUF builds of [mistralai/Voxtral-Mini-3B-2507](https://huggingface.co/mistralai/Voxtral-Mini-3B-2507)
 for [voxtral.cpp](https://github.com/andrijdavid/voxtral.cpp), a ggml-based C++
@@ -36,7 +36,7 @@ decoder that transcribes by generating text tokens and very fast for batch / lon
 | --- | --- |
 | `Q8_0` | near-lossless, largest |
 | `Q6_K`, `Q5_K`, `Q5_1`, `Q5_0` | high quality |
-| **`Q4_K_M`** | **recommended** — best size/quality trade-off |
 | `Q4_K`, `Q4_1`, `Q4_0` | smaller |
 | `Q3_K` | smallest usable (some quality loss) |

   - it
 ---
+# Voxtral-Mini-3B-2507-GGUF
 GGUF builds of [mistralai/Voxtral-Mini-3B-2507](https://huggingface.co/mistralai/Voxtral-Mini-3B-2507)
 for [voxtral.cpp](https://github.com/andrijdavid/voxtral.cpp), a ggml-based C++
 | --- | --- |
 | `Q8_0` | near-lossless, largest |
 | `Q6_K`, `Q5_K`, `Q5_1`, `Q5_0` | high quality |
+| **`Q4_K_M`** | **recommended** best size/quality trade-off |
 | `Q4_K`, `Q4_1`, `Q4_0` | smaller |
 | `Q3_K` | smallest usable (some quality loss) |