Only with CPU offload
Ministral 3 14B at Q4_K_M needs 9.7 GB but only 5.3 GB is addressable, so about 56% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 7.3 tokens per second — usable for batch work, painful for chat.
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.
Fits instead: Ministral 3 3B (3.6 GB)
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 25.9 GB | 27.7 GB | — | ~1.6 | Reference | 22.4 GB over |
| Q8_0 | 13.8 GB | 15.6 GB | — | ~3.3 | −0.1% ppl | 10.3 GB over |
| Q6_K | 10.6 GB | 12.5 GB | — | ~4.7 | −0.4% ppl | 7.2 GB over |
| Q5_K_M | 9.2 GB | 11.0 GB | — | ~5.7 | −0.8% ppl | 5.7 GB over |
| Q4_K_M | 7.8 GB | 9.7 GB | — | ~7.3 | −1.9% ppl | 4.4 GB over |
| Q3_K_M | 6.3 GB | 8.2 GB | — | ~10 | −5.4% ppl | 2.9 GB over |
| Q2_K | 5.4 GB | 7.3 GB | — | ~14 | −15% ppl | 2.0 GB over |
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
$ llama-server \
-hf mistralai/Ministral-3-14B-Instruct-2512:Q4_K_M \
-c 8192 -ngl 17
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a GeForce RTX 3060 Laptop
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Ministral 3 8B 8.92B · same family |
Q4_K_M · 6.7 GB | ~18 | CPU offload |
| Ministral 3 3B 3.85B · same family |
Q4_K_M · 3.6 GB | 94 | Runs great |
| Phi-4 14B 14.7B · similar size |
Q4_K_M · 10.4 GB | ~6.4 | CPU offload |
| Qwen3 14B 14.8B · similar size |
Q4_K_M · 10.2 GB | ~6.6 | CPU offload |
| DeepSeek-R1-Distill-Qwen 14B 14.8B · similar size |
Q4_K_M · 10.4 GB | ~6.4 | CPU offload |
| Qwen2.5-Coder 14B 14.8B · similar size |
Q4_K_M · 10.4 GB | ~6.4 | CPU offload |
| Gemma 3 12B 12.2B · similar size |
Q4_K_M · 8.3 GB | ~9.9 | CPU offload |
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 |