Mistral Small 4 (119B) Hardware Requirements
Mistral's one-model-to-rule-them-all for 2026: chat, reasoning with configurable effort, vision, and coding folded into a 119B MoE with just 6B active. "Small" is marketing — this wants unified memory or dual GPUs.
VRAM needed (Q4, 8k context)
74.3 GB
No single consumer GPU fits this model — see multi-GPU and Mac options below.
Updated July 2026. Estimates — see methodology below.
VRAM by Quantization
Weights + KV cache at 8k context + 1.2GB system overhead. Q4_K_M is the community default — quality loss is negligible for most use.
| Quantization | Weights | KV cache (8k) | Total VRAM | Cheapest GPU that fits |
|---|---|---|---|---|
| Q4_K_M Recommended — near-lossless for most use, half the size of Q8 | 72.1 GB | 0.9 GB | 74.3 GB | Multi-GPU / Mac territory |
| Q5_K_M Slightly higher quality than Q4 for ~18% more VRAM | 84.8 GB | 0.9 GB | 86.9 GB | Multi-GPU / Mac territory |
| Q8_0 Effectively lossless — use if you have VRAM to spare | 126 GB | 0.9 GB | 129 GB | Multi-GPU / Mac territory |
| FP16 Full precision — only for fine-tuning or maximum fidelity | 238 GB | 0.9 GB | 240 GB | Multi-GPU / Mac territory |
Longer context costs VRAM
KV cache grows linearly with context: 8k → 0.9 GB · 32k → 3.8 GB · 128k → 15.0 GB. If you plan to feed whole documents or codebases, size your GPU for the context you actually need, not just the weights.
Why Mistral Small 4 (119B) is fast but VRAM-hungry
Mistral Small 4 (119B) is a Mixture-of-Experts model: all 119B parameters must sit in memory, but each token only activates 6B of them. Memory capacity requirements are those of a 119B model, while speed is that of a 6B model — which is why MoE models feel so fast when they fit, and why Macs with large unified memory punch above their weight running them.
GPU Compatibility (Q4, 8k context)
Every GPU in our database, scored against Mistral Small 4 (119B). Speed is estimated decode rate — memory-bandwidth-bound, so VRAM and bandwidth matter more than shader count.
| GPU | VRAM | Verdict | Est. speed | Price | |
|---|---|---|---|---|---|
| RTX 3060 | 12 GB | Not enough VRAM | — | ~$238 used | |
| Arc B570 | 10 GB | Not enough VRAM | — | from $225 | |
| RTX 4060 | 8 GB | Not enough VRAM | — | ~$275 used | |
| RX 7600 | 8 GB | Not enough VRAM | — | from $250 | |
| Arc B580 | 12 GB | Not enough VRAM | — | from $250 | |
| RX 6700 XT | 12 GB | Not enough VRAM | — | ~$315 used | |
| Arc A770 | 16 GB | Not enough VRAM | — | from $300 | |
| RTX 4060 Ti | 8 GB | Not enough VRAM | — | ~$338 used | |
| RTX 3070 | 8 GB | Not enough VRAM | — | ~$338 used | |
| RTX 5060 | 8 GB | Not enough VRAM | — | from $325 | |
| RX 7700 XT | 12 GB | Not enough VRAM | — | ~$415 used | |
| RX 6800 XT | 16 GB | Not enough VRAM | — | ~$438 used | |
| RTX 3080 | 10 GB | Not enough VRAM | — | ~$463 used | |
| RX 7800 XT | 16 GB | Not enough VRAM | — | ~$488 used | |
| RTX 4070 | 12 GB | Not enough VRAM | — | ~$500 used | |
| RTX 4070 SUPER | 12 GB | Not enough VRAM | — | ~$563 used | |
| RX 7900 XT | 20 GB | Not enough VRAM | — | ~$588 used | |
| RTX 5060 Ti | 16 GB | Not enough VRAM | — | from $550 | |
| RX 9070 | 16 GB | Not enough VRAM | — | from $575 | |
| RTX 5070 | 12 GB | Not enough VRAM | — | from $600 | |
| RX 9070 XT | 16 GB | Not enough VRAM | — | from $600 | |
| RTX 4070 Ti SUPER | 16 GB | Not enough VRAM | — | ~$750 used | |
| RX 7900 XTX | 24 GB | Not enough VRAM | — | ~$838 used | |
| RTX 4080 SUPER | 16 GB | Not enough VRAM | — | ~$900 used | |
| RTX 5070 Ti | 16 GB | Not enough VRAM | — | from $900 | |
| RTX 3090 | 24 GB | Not enough VRAM | — | ~$1,150 used | |
| RTX 5080 | 16 GB | Not enough VRAM | — | from $1,250 | |
| RTX 4090 | 24 GB | Not enough VRAM | — | ~$2,375 used | |
| RTX 5090 | 32 GB | Not enough VRAM | — | from $2,800 |
Frequently Asked Questions
How much VRAM do I need to run Mistral Small 4 (119B)?+
At the recommended Q4_K_M quantization with 8k context, Mistral Small 4 (119B) needs roughly 74.3GB of VRAM (72.1GB weights + KV cache + overhead). Q8 needs about 129GB and full FP16 about 240GB.
Can any single consumer GPU run Mistral Small 4 (119B)?+
No single consumer GPU currently has enough VRAM to run Mistral Small 4 (119B) fully. Realistic options: a multi-GPU rig (e.g. dual 24GB cards), a Mac with enough unified memory, or a 128GB Ryzen AI Max "Strix Halo" mini-PC — the 2026 favorite for exactly this class of model.
Can I run Mistral Small 4 (119B) on an RTX 3060?+
No — 12GB is well below what Mistral Small 4 (119B) needs even at Q4 quantization.
Can I run Mistral Small 4 (119B) on a Mac?+
Yes, if the Mac has enough unified memory: budget roughly 74.3GB of RAM for the Q4 version (plus what macOS itself uses). Apple Silicon runs GGUF models well via Ollama or LM Studio, and MoE models like this one are particularly Mac-friendly — only 6B parameters are active per token, so memory bandwidth goes further.
Can I run Mistral Small 4 (119B) on CPU only?+
Sort of. Because only 6B of 119B parameters are active per token, CPU inference is more viable than for dense models this size — expect single-digit tokens/sec with fast DDR5. A GPU is still dramatically better.
Is Mistral Small 4 (119B) free for commercial use?+
Yes. Mistral Small 4 (119B) is released under the Apache 2.0, which permits commercial use.
Related Models
How we calculate these numbers
VRAM = model weights (parameters × bits per weight ÷ 8) + KV cache (architecture-specific bytes per token × context length) + ~1.2GB runtime overhead. Speed estimates assume decode is memory-bandwidth-bound at ~50% utilization (lower for MoE models, which pay routing overhead), matching typical llama.cpp performance on consumer cards; real results vary with runtime, drivers, and settings. Quant sizes reflect GGUF K-quants, which keep some layers at higher precision. Figures are estimates for planning, not guarantees — when in doubt, buy more VRAM than you need today. Prices shown are launch MSRP; mid-2026 street prices often run well above MSRP due to the ongoing memory shortage, and used 24GB cards are holding their value unusually well.