Mistral AI · Chat and reasoning · 675B parameters · 41B active · apache-2.0
Mistral Large 3 675B Instruct 2512
Needs 818 GB at FP8 / INT8. The smallest real configuration today is 4× MI325X at Cyfuture AI, $12.29 per hour, about $8,972 a month at 730 hours.
Parameters675B41B active per token
Context288k tokensmaximum published
Checkpoint682 GBFP8, as published
Licenseapache-2.0check before commercial use
Released—documented date
Smallest configuration · FP8 / INT8
4× MI325X1024 GB VRAM · 80% used
- Per hour
- $12.29
- Per month
- $8,972
- Cheapest at
Cyfuture AI
Memory · 2 precisionsHow much VRAM it needs
Weights plus runtime overhead. The context dimension appears once the model's architecture is on file.
| Precision | Weights | Weights + headroom |
|---|---|---|
| FP8published checkpoint | 682 GB | 818 GB |
| INT4 / MXFP4estimated | 405 GB | 486 GB |
Cross-checked on Hugging Face Oct 28, 2026: repository read, 681.5 GB of weight files. Method: weights as published at the native precision, verified on Hugging Face 2026-10-28; other precisions estimated at 1 (8-bit) and 0.6 (4-bit) bytes per parameter; × 1.2 runtime headroom; KV cache not added (architecture not readable).
Smallest configuration per GPU · 109 GPUs · cheapest eligible on-demand offer per GPU count, every provider on fileWhat it costs to run, GPU by GPU
The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| MI325XBest fit | 4× 256 GB1024 GB total | 80% | $12.29 | $8,972 | Cyfuture AInot scored · read Nov 2 · receipt |
| MI300X | 8× 192 GB1536 GB total | 53% | $13.68 | $9,986 |  TensorWaveTrust 64 · read Nov 2 · receipt · also Cyfuture AI $22.38, AtmosCompute $26.77 |
| H200 | 8× 141 GB1128 GB total | 73% | $21.04 | $15,359 |  Airon AInot scored · read Nov 2 · receipt · also Geodd $21.76, Lium $23.92 |
| B300 | 4× 270 GB1080 GB total | 76% | $23.29 | $17,004 |  UpCloudTrust 75 · read Nov 2 · receipt · also FPT AI Factory $27.96, Verda $45.40 |
| MI355X | 8× 288 GB2304 GB total | 35% | $23.60 | $17,228 | TensorWaveTrust 64 · read Nov 2 · receipt |
| H200 NVL | 8× 141 GB1128 GB total | 73% | $26.09 | $19,042 |  IONOSnot scored · read Nov 2 · receipt · also Geodd $27.12, Vast.ai $39.47 |
| B200 | 8× 180 GB1440 GB total | 57% | $32.91 | $24,026 | UpCloudTrust 75 · read Nov 2 · receipt · also Airon AI $33.04, Deep Infra $39.12 |
| B300 CC | 4× 270 GB1080 GB total | 76% | $46.31 | $33,806 |  VerdaTrust 81 · read Nov 2 · receipt |
| GB300 | 4× 279 GB1116 GB total | 73% | $52.21 | $38,113 | VerdaTrust 81 · read Nov 2 · receipt |
| B200 CC | 8× 180 GB1440 GB total | 57% | $72.37 | $52,830 | VerdaTrust 81 · read Nov 2 · receipt |
Throughput estimates · Oct 4, 2026Tokens per second, and what a million costs
Chat and reasoning. Speed estimated from memory bandwidth and model size, never measured. The cost per 1M output tokens is an estimate at the prices read on Oct 4, 2026; it is not recomputed here.
| GPU | Cards | Precision | tok/s per user | per 1M output tokens · estimate |
|---|---|---|---|---|
| MI300X | 8 | FP8 | 32.9 | $4.00 |
| H200 | 8 | FP8 | 42.6 | $4.90 |
| B200 | 8 | FP8 | 57.4 | $5.29 |
cards, precision and speed estimated from memory bandwidth and model size; cost recomputed by the site from verified prices · cheapest per output at the prices of Oct 4, 2026: MI300XWhy estimates, and their limits →
Mistral Large 3 675B Instruct 2512 · related