Can you run Devstral 2 123B Instruct locally?

Devstral 2 family · 2025 · 125B parameters (125B activated per token) · Hugging Face model card

How much VRAM does Devstral 2 123B Instruct need at each quantization?

Devstral 2 123B Instruct needs 84.0 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.

yarn factor=64 original_max_position_embeddings=4096; GQA 96/8

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 2026-10-06 via api (gated=false private=false params=125.03B safetensors.total=125025989840 ctx=262144 license=other repo=mistralai/Devstral-2-123B-Instruct-2512@1613bf01adb5e1c6fdc196b46e6b173eae75eb4a layers=88 hidden=12288 heads=96 kv_heads=8 experts=None per_tok=None). active_params_b=125.03 (dense model; total params used). VRAM figures are documented calculations (Q4-class, 0.6 GB per B params), not measurements. No tok/s invented.

Which GPUs can run Devstral 2 123B Instruct locally?

At Q4_K_M with a 4k context, Devstral 2 123B Instruct needs 84.0 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 Devstral 2 123B Instruct comfortably (25%+ VRAM headroom)

Minimum GPUs that fit Devstral 2 123B Instruct at Q4_K_M

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

Needs 2+ GPUs to run Devstral 2 123B Instruct

One of these cards is too small on its own, but a pair (tensor or pipeline parallel, ~90% efficiency) covers the 84.0 GB requirement. See our multi-GPU guide for setup.

Can a Mac run Devstral 2 123B Instruct?

Yes — these Apple Silicon machines fit Devstral 2 123B Instruct 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 Devstral 2 123B Instruct run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for Devstral 2 123B Instruct 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 Devstral 2 123B Instruct?

These mini PCs and workstations from our database fit Devstral 2 123B Instruct 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