Ministral 3 14B needs ~21.4 GB VRAM. NVIDIA H100 PCIe 80GB has 80.0 GB. With Q4_K_M quantization, expect ~157 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
169.2 tok/s
TTFT
1144 ms
Safe context
262K
Memory
21.4 GB / 80.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 169.2 tok/s | 624 ms | 262K |
| Coding | A | Runs well | 157.4 tok/s | 1230 ms | 262K |
| Agentic Coding | A | Runs well | 169.2 tok/s | 1664 ms | 262K |
| Reasoning | A | Runs well | 169.2 tok/s | 1352 ms | 262K |
| RAG | A | Runs well | 169.2 tok/s | 2081 ms | 262K |
How Ministral 3 14B (14B params) fits at each quantization level on NVIDIA H100 PCIe 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | A75 |
Q3_K_S | 3 | 6.9 GB | Low | A75 |
NVFP4 | 4 |
Copy-paste commands to run Ministral 3 14B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "mistralai/Ministral-3-14B-Instruct-2512" \
--hf-file "Ministral-3-14B-Instruct-2512-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 30.5B | S | 193.1 tok/s | ||
| 27B | S | 88.1 tok/s |
Yes, NVIDIA H100 PCIe 80GB can run Ministral 3 14B with a A grade (Runs well). Expected decode speed: 157.4 tok/s.
Ministral 3 14B (14B parameters) requires approximately 21.4 GB of memory with Q4_K_M quantization.
The recommended quantization for Ministral 3 14B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA H100 PCIe 80GB, Ministral 3 14B achieves approximately 157.4 tokens per second decode speed with a time-to-first-token of 1230ms using Q4_K_M quantization.
For coding workloads, Ministral 3 14B on NVIDIA H100 PCIe 80GB receives a A grade with 157.4 tok/s and 262K context.
On NVIDIA H100 PCIe 80GB, Ministral 3 14B can safely use up to 262K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/ministral-3-14b-on-h100-pcie-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| Medium |
| A75 |
Q4_K_M | 4 | 8.5 GB | Medium | A75 |
Q5_K_M | 5 | 10.1 GB | High | A75 |
Q6_K | 6 | 11.5 GB | High | A75 |
Q8_0 | 8 | 15.0 GB | Very High | A76 |
F16Best for your GPU | 16 | 28.7 GB | Maximum | A78 |
| 27B | S | 88.4 tok/s |
| 35B | S | 162.3 tok/s |
| 30B | S | 199.7 tok/s |