Ministral 3 14B needs ~19.8 GB VRAM. AMD Instinct MI210 64GB has 64.0 GB. With Q4_K_M quantization, expect ~104 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
112.2 tok/s
TTFT
1726 ms
Safe context
262K
Memory
19.8 GB / 64.0 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 | 112.2 tok/s | 941 ms | 262K |
| Coding | A | Runs well | 104.3 tok/s | 1855 ms | 262K |
| Agentic Coding | A | Runs well | 112.2 tok/s | 2511 ms | 262K |
| Reasoning | A | Runs well | 112.2 tok/s | 2040 ms | 262K |
| RAG | A | Runs well | 112.2 tok/s | 3138 ms | 262K |
How Ministral 3 14B (14B params) fits at each quantization level on AMD Instinct MI210 64GB (64.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | A76 |
Q3_K_S | 3 | 6.9 GB | Low | A76 |
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 | 128 tok/s | ||
| 27B | S | 58.4 tok/s |
Yes, AMD Instinct MI210 64GB can run Ministral 3 14B with a A grade (Runs well). Expected decode speed: 104.3 tok/s.
Ministral 3 14B (14B parameters) requires approximately 19.8 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 AMD Instinct MI210 64GB, Ministral 3 14B achieves approximately 104.3 tokens per second decode speed with a time-to-first-token of 1855ms using Q4_K_M quantization.
For coding workloads, Ministral 3 14B on AMD Instinct MI210 64GB receives a A grade with 104.3 tok/s and 262K context.
On AMD Instinct MI210 64GB, 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-instinct-mi210-64gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
7.8 GB |
| Medium |
| A76 |
Q4_K_M | 4 | 8.5 GB | Medium | A76 |
Q5_K_M | 5 | 10.1 GB | High | A76 |
Q6_K | 6 | 11.5 GB | High | A77 |
Q8_0 | 8 | 15.0 GB | Very High | A77 |
F16Best for your GPU | 16 | 28.7 GB | Maximum | A80 |
| 27B | S | 58.6 tok/s |
| 35B | S | 107.6 tok/s |
| 30B | S | 132.4 tok/s |