Loading…
Loading…
Models / Ministral-3
3 models (3B to 14B) · ↓ 10.8K downloads a month · from $0.08/h on GTX 1660 SUPER right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| ministral3 3B oga (SamTheDev)SamTheDev/ministral3-3B-oga | ONNX Runtime GenAI | 2.0 GB | 4.7 GB | $0.08/h GTX 1660 SUPER |
| ministral 3 3b instruct genai int4 (hyperquader)hyperquader/ministral-3-3b-instruct-genai-int4 | ONNX Runtime GenAI | 2.0 GB | 4.7 GB | $0.08/h GTX 1660 SUPER |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| ministral 3 8b instruct genai int4 (hyperquader)hyperquader/ministral-3-8b-instruct-genai-int4 | ONNX Runtime GenAI | 5.6 GB | 9.1 GB | $0.08/h GTX 1080 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Ministral 3 14B Instruct 2512 FP8 dynamic (RedHatAI)RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic | vLLM | 18 GB | 23.5 GB | $0.19/h RTX 3090 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").