Card accuracy pass 2: remove unmeasured speed claims, honest brand labels
Browse files
README.md
CHANGED
|
@@ -98,4 +98,11 @@ for chunk in audio_stream():
|
|
| 98 |
- [`majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-8bit`](https://huggingface.co/majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-8bit)
|
| 99 |
- [`majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-2bit`](https://huggingface.co/majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-2bit)
|
| 100 |
- [`majentik/Voxtral-Mini-4B-Realtime-2602-RotorQuant-MLX-4bit`](https://huggingface.co/majentik/Voxtral-Mini-4B-Realtime-2602-RotorQuant-MLX-4bit)
|
| 101 |
-
- [`mistralai/Voxtral-Mini-4B-Realtime-2602`](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602) — upstream base model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
- [`majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-8bit`](https://huggingface.co/majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-8bit)
|
| 99 |
- [`majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-2bit`](https://huggingface.co/majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-2bit)
|
| 100 |
- [`majentik/Voxtral-Mini-4B-Realtime-2602-RotorQuant-MLX-4bit`](https://huggingface.co/majentik/Voxtral-Mini-4B-Realtime-2602-RotorQuant-MLX-4bit)
|
| 101 |
+
- [`mistralai/Voxtral-Mini-4B-Realtime-2602`](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602) — upstream base model
|
| 102 |
+
|
| 103 |
+
## About the RotorQuant / TurboQuant labels
|
| 104 |
+
|
| 105 |
+
RotorQuant and TurboQuant are this project's **release labels**, not distinct
|
| 106 |
+
quantization algorithms — for any given tier, both brand repos carry
|
| 107 |
+
byte-identical weights produced with the standard MLX / llama.cpp quantizers.
|
| 108 |
+
No brand-specific speedup is claimed or measured.
|