What hardware runs Mistral Large 3?
Mistral Large 3 is a 673.42B-parameter mixture-of-experts model with 39.95B active parameters (apache-2.0 license). Mistral's 675B MLA+MoE flagship. European frontier weight class — and a cloud referral for all but server rigs.
All figures assume an f16 KV cache, a 0.6 GB display reserve on the GPU, and 64 GB of DDR5 system RAM for the offload tiers. Tune these in the calculator.
Minimum VRAM by quant and context
| Quant | File size | 8K | 16K | 32K | 64K | 128K |
|---|---|---|---|---|---|---|
| Q2_K * | 230.1 GB | 234 GB | 234.8 GB | 235.8 GB | 238 GB | 242.3 GB |
| Q3_K_M | 299.7 GB | 303.6 GB | 304.4 GB | 305.4 GB | 307.6 GB | 311.9 GB |
| Q4_K_M | 379.0 GB | 382.9 GB | 383.7 GB | 384.7 GB | 386.9 GB | 391.2 GB |
| Q5_K_M | 445.1 GB | 449 GB | 449.8 GB | 450.8 GB | 453 GB | 457.3 GB |
| Q6_K | 515.3 GB | 519.2 GB | 519.9 GB | 521 GB | 523.2 GB | 527.4 GB |
| Q8_0 | 666.5 GB | 670.4 GB | 671.1 GB | 672.2 GB | 674.4 GB | 678.7 GB |
| IQ4_XS | 335.2 GB | 339.1 GB | 339.9 GB | 340.9 GB | 343.1 GB | 347.4 GB |
Full-GPU figures: weights + f16 KV cache + overhead. * below our recommended floor of Q3_K_M.
GPU compatibility
Fits on GPUExpert offloadPartial offloadCPU only
Quant guidance
Our floor for Mistral Large 3 is Q3_K_M — below that, quality degrades faster than the VRAM savings are worth (large models tolerate low bpw better than small ones, which is why the floor is lower here). Prefer the highest quant that still lands "Fits on GPU" or “Expert offload” at your context length in the table above.
Frequently asked questions
How much VRAM does Mistral Large 3 need?
At Q3_K_M and 32K context, Mistral Large 3 needs about 305.4 GB of VRAM to run fully on GPU (weights + KV cache + overhead). As a mixture-of-experts model it can also run with far less VRAM via expert offload, keeping experts in system RAM.
What is the smallest GPU that can run Mistral Large 3?
No single consumer GPU in our set runs Mistral Large 3 well — it's a cloud-rental or multi-GPU model.
What quantization should I use for Mistral Large 3?
We recommend Q3_K_M or higher. Q4_K_M weighs 379.0 GB (4.83 bits/weight); going below Q3_K_M costs noticeable quality on a model this size.
How long a context can Mistral Large 3 handle?
Mistral Large 3 supports up to 288K tokens. KV cache grows linearly with context, though its MLA attention compresses the KV cache dramatically.
Can I run Mistral Large 3 without a GPU?
Not realistically — even at 8K context the weights don't fit in 64 GB of system RAM.