Can you run Mistral Small 4 119B-A6.5B locally?

Mistral Small 4 family · 2026 · 119.4B parameters (6.5B activated per token) · Hugging Face model card

How much VRAM does Mistral Small 4 119B-A6.5B need at each quantization?

Mistral Small 4 119B-A6.5B needs 81.2 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.

Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (36 layers, 32 KV heads, 128 head dim). Source: HF-verified 2026-09-28 via api (gated=false private=false params=119.4B safetensors.total=119401317952 downloadable_safetensors_sum=241850185032 ctx=1048576 license=apache-2.0 repo=mistralai/Mistral-Small-4-119B-2603@a11f36bebf709121056b1dbcc943d1c6afbe494d layers=36 kv_heads=32). MoE: num_experts=128 num_experts_per_tok=4 active_params_b=6.5 (vendor card; VRAM fit uses active, not dense-equivalent). VRAM figures are documented calculations, not measurements. No tok/s invented.

Which GPUs can run Mistral Small 4 119B-A6.5B locally?

At Q4_K_M with a 4k context, Mistral Small 4 119B-A6.5B needs 81.2 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.

Runs Mistral Small 4 119B-A6.5B comfortably (25%+ VRAM headroom)

Minimum GPUs that fit Mistral Small 4 119B-A6.5B at Q4_K_M

These GPUs hold the model but leave little headroom — keep contexts short.

Needs 2+ GPUs to run Mistral Small 4 119B-A6.5B

One of these cards is too small on its own, but a pair (tensor or pipeline parallel, ~90% efficiency) covers the 81.2 GB requirement. See our multi-GPU guide for setup.

Can a Mac run Mistral Small 4 119B-A6.5B?

Yes — these Apple Silicon machines fit Mistral Small 4 119B-A6.5B at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.

Can Mistral Small 4 119B-A6.5B run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for Mistral Small 4 119B-A6.5B at Q4_K_M. Their memory bandwidth is far below discrete GPUs, so expect a fraction of desktop generation speed.

Which pre-built systems can run Mistral Small 4 119B-A6.5B?

These mini PCs and workstations from our database fit Mistral Small 4 119B-A6.5B at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.

Frequently asked questions