Ministral 3 14B needs ~16.6 GB VRAM. NVIDIA V100 32GB has 32.0 GB. With Q4_K_M quantization, expect ~61 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
60.7 tok/s
TTFT
3188 ms
Safe context
117K
Memory
16.6 GB / 32.0 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 | S | Runs well | 60.7 tok/s | 1739 ms | 117K |
| Coding | S | Runs well | 60.7 tok/s | 3188 ms | 117K |
| Agentic Coding | S | Runs well | 60.7 tok/s | 4637 ms | 117K |
| Reasoning | S | Runs well | 60.7 tok/s | 3768 ms | 117K |
| RAG | S | Runs well | 60.7 tok/s | 5797 ms | 117K |
Inference speed
Estimated decode speed (tokens/sec) for Ministral 3 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~121 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 120.9 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 87.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 77.1 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 70.1 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 66.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 61.5 | Tight |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 58.4 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 55.4 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 38.1 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 38.1 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 30.2 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 27.7 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 25.9 | Heavy offload |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 23.3 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 16.3 | Heavy offload |
| RTX 4060 8GB | 8 GB | Q4_K_M | 4.5 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Ministral 3 14B (14B params) fits at each quantization level on NVIDIA V100 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | A79 |
Q3_K_S | 3 | 6.9 GB | Low | A79 |
NVFP4 | 4 | 7.8 GB | Medium | A80 |
Q4_K_M | 4 | 8.5 GB | Medium | A80 |
Q5_K_M | 5 | 10.1 GB | High | A81 |
Q6_K | 6 | 11.5 GB | High | A82 |
Q8_0Best for your GPU | 8 | 15.0 GB | Very High | A83 |
F16 | 16 | 28.7 GB | Maximum | F0 |
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 |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 69.3 tok/s | |
| Qwen 3.5 27B | 27B | S | 31.6 tok/s | |
| Qwen 3.6 27B | 27B | S | 31.7 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 71.7 tok/s | |
| Qwen 3.5 35B A3B | 35B | S | 63.3 tok/s |
Yes, NVIDIA V100 32GB can run Ministral 3 14B with a S grade (Runs well). Expected decode speed: 60.7 tok/s.
Ministral 3 14B (14B parameters) requires approximately 16.6 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 V100 32GB, Ministral 3 14B achieves approximately 60.7 tokens per second decode speed with a time-to-first-token of 3188ms using Q4_K_M quantization.
For coding workloads, Ministral 3 14B on NVIDIA V100 32GB receives a S grade with 60.7 tok/s and 117K context.
On NVIDIA V100 32GB, Ministral 3 14B can safely use up to 117K 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-v100-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: