Can you run Mistral Medium 3.5 128B locally?

Mistral Medium 3.5 family · 2026 · 127.7B parameters (127.7B activated per token) · Hugging Face model card

How much VRAM does Mistral Medium 3.5 128B need at each quantization?

Mistral Medium 3.5 128B needs 85.8 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 (88 layers, 8 KV heads, 128 head dim). Source: HF-verified 2026-09-28 via api (gated=false private=false params=127.7B safetensors.total=127704210176 downloadable_safetensors_sum=267212267176 ctx=262144 license=other repo=mistralai/Mistral-Medium-3.5-128B@22b2b868a15677cfa6061277ed2f653d1349a9ab layers=88 kv_heads=8). MoE: num_experts=None num_experts_per_tok=None active_params_b=127.7 (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 Medium 3.5 128B locally?

At Q4_K_M with a 4k context, Mistral Medium 3.5 128B needs 85.8 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 Medium 3.5 128B comfortably (25%+ VRAM headroom)

Minimum GPUs that fit Mistral Medium 3.5 128B at Q4_K_M

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

Needs 2+ GPUs to run Mistral Medium 3.5 128B

One of these cards is too small on its own, but a pair (tensor or pipeline parallel, ~90% efficiency) covers the 85.8 GB requirement. See our multi-GPU guide for setup.

Can a Mac run Mistral Medium 3.5 128B?

Yes — these Apple Silicon machines fit Mistral Medium 3.5 128B 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 Medium 3.5 128B run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for Mistral Medium 3.5 128B 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 Medium 3.5 128B?

These mini PCs and workstations from our database fit Mistral Medium 3.5 128B 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