Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,8 @@ This model is the instruct post-trained version, fine-tuned for instruction task
|
|
| 30 |
|
| 31 |
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 14B can even be deployed locally, capable of fitting in 32GB of VRAM in BF16, and less than 24GB of RAM/VRAM when quantized.
|
| 32 |
|
|
|
|
|
|
|
| 33 |
## Key Features
|
| 34 |
Ministral 3 14B consists of two main architectural components:
|
| 35 |
- **13.5B Language Model**
|
|
@@ -59,17 +61,16 @@ Bringing advanced AI capabilities to most environments.
|
|
| 59 |
|--------------------------------|--------------------|-----------|------------------------------------------------------------------------------------------|
|
| 60 |
| Ministral 3 3B Base 2512 | Base pre-trained | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Base-2512) |
|
| 61 |
| Ministral 3 3B Instruct 2512 | Instruct post-trained | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512) |
|
| 62 |
-
| - Ministral 3 3B Instruct 2512 FP8 | Instruct post-trained | FP8 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512-FP8) |
|
| 63 |
| Ministral 3 3B Reasoning 2512 | Reasoning capable | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512) |
|
| 64 |
| Ministral 3 8B Base 2512 | Base pre-trained | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Base-2512) |
|
| 65 |
| Ministral 3 8B Instruct 2512 | Instruct post-trained | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512) |
|
| 66 |
-
| - Ministral 3 8B Instruct 2512 FP8 | Instruct post-trained | FP8 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512-FP8) |
|
| 67 |
| Ministral 3 8B Reasoning 2512 | Reasoning capable | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Reasoning-2512) |
|
| 68 |
| Ministral 3 14B Base 2512 | Base pre-trained** | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Base-2512) |
|
| 69 |
| **Ministral 3 14B Instruct 2512** | **Instruct post-trained** | **BF16** | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512) |
|
| 70 |
-
| - Ministral 3 14B Instruct 2512 FP8 | Instruct post-trained | FP8 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512-FP8) |
|
| 71 |
| Ministral 3 14B Reasoning 2512 | Reasoning capable | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Reasoning-2512) |
|
| 72 |
|
|
|
|
|
|
|
| 73 |
## Benchmark Results
|
| 74 |
|
| 75 |
We compare Ministral 3 to similar sized models.
|
|
|
|
| 30 |
|
| 31 |
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 14B can even be deployed locally, capable of fitting in 32GB of VRAM in BF16, and less than 24GB of RAM/VRAM when quantized.
|
| 32 |
|
| 33 |
+
We provide a no-loss FP8 version [here](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512-FP8), you can find other formats and quantizations in the [Ministral 3 - Quants](https://huggingface.co/collections/mistralai/ministral-3-quants) collection.
|
| 34 |
+
|
| 35 |
## Key Features
|
| 36 |
Ministral 3 14B consists of two main architectural components:
|
| 37 |
- **13.5B Language Model**
|
|
|
|
| 61 |
|--------------------------------|--------------------|-----------|------------------------------------------------------------------------------------------|
|
| 62 |
| Ministral 3 3B Base 2512 | Base pre-trained | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Base-2512) |
|
| 63 |
| Ministral 3 3B Instruct 2512 | Instruct post-trained | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512) |
|
|
|
|
| 64 |
| Ministral 3 3B Reasoning 2512 | Reasoning capable | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512) |
|
| 65 |
| Ministral 3 8B Base 2512 | Base pre-trained | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Base-2512) |
|
| 66 |
| Ministral 3 8B Instruct 2512 | Instruct post-trained | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512) |
|
|
|
|
| 67 |
| Ministral 3 8B Reasoning 2512 | Reasoning capable | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Reasoning-2512) |
|
| 68 |
| Ministral 3 14B Base 2512 | Base pre-trained** | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Base-2512) |
|
| 69 |
| **Ministral 3 14B Instruct 2512** | **Instruct post-trained** | **BF16** | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512) |
|
|
|
|
| 70 |
| Ministral 3 14B Reasoning 2512 | Reasoning capable | BF16 | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Reasoning-2512) |
|
| 71 |
|
| 72 |
+
Other formats available [here](https://huggingface.co/collections/mistralai/ministral-3-quants).
|
| 73 |
+
|
| 74 |
## Benchmark Results
|
| 75 |
|
| 76 |
We compare Ministral 3 to similar sized models.
|