Yes — with 68.7 GB to spare
Ministral 3 14B at Q4_K_M fits your H100 SXM entirely on the GPU at 8K context, at an estimated 259 tokens per second. There is room for its full 256K window.
Fully on GPU
8K context
Q4_K_M · 7.8 GB
Apache 2.0
Released Dec 2025
Vision
The largest Ministral. A 12 GB card runs it at Q4 with a few gigabytes to spare.
Hardware requirements What hardware do I need to run Ministral 3 14B? →At Q4_K_M with an 8K context: a 16 GB GPU (RTX 5080) or a 24 GB Mac (M4 Pro). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
weights 7.8 GB
Weights 7.8 GB
KV cache @ 8K 1.25 GB
Runtime overhead 0.6 GB
Free 68.7 GB of 78.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 25.9 GB | 27.7 GB | 256K | 78 | Reference | Long context |
| Q8_0 | 13.8 GB | 15.6 GB | 256K | 147 | −0.1% ppl | Long context |
| Q6_K | 10.6 GB | 12.5 GB | 256K | 191 | −0.4% ppl | Long context |
| Q5_K_M | 9.2 GB | 11.0 GB | 256K | 221 | −0.8% ppl | Long context |
| Q4_K_M | 7.8 GB | 9.7 GB | 256K | 259 | −1.9% ppl | Recommended |
| Q3_K_M | 6.3 GB | 8.2 GB | 256K | 321 | −5.4% ppl | Long context |
| Q2_K | 5.4 GB | 7.3 GB | 256K | 374 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ ollama pull ministral-3:14b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run ministral-3:14b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 7.8 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to the model's full 256K context on this card.
Related models on an H100 SXM
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Ministral 3 8B 8.92B · same family |
Q4_K_M · 6.7 GB | 404 | Runs great |
| Ministral 3 3B 3.85B · same family |
Q4_K_M · 3.6 GB | 937 | Runs great |
| Phi-4 14B 14.7B · similar size |
Q4_K_M · 10.4 GB | 245 | Runs great |
| Qwen3 14B 14.8B · similar size |
Q4_K_M · 10.2 GB | 244 | Runs great |
| DeepSeek-R1-Distill-Qwen 14B 14.8B · similar size |
Q4_K_M · 10.4 GB | 244 | Runs great |
| Qwen2.5-Coder 14B 14.8B · similar size |
Q4_K_M · 10.4 GB | 244 | Runs great |
| Gemma 3 12B 12.2B · similar size |
Q4_K_M · 8.3 GB | 296 | Runs great |
Ministral 3 14B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
9.7 GB | ~9.4 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
9.7 GB | 28 | Tight fit |
| GeForce RTX 5080 14.4 GB usable · 960 GB/s |
9.7 GB | 74 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
9.7 GB | 8.6 | Tight fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
9.7 GB | 78 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
9.7 GB | 74 | Runs great |
| M4 Pro · 24 GB 18.0 GB usable · 273 GB/s |
9.7 GB | 20 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
9.7 GB | 29 | Runs great |