// Mistral / Magistral / Devstral · Text LLM
Mistral-Large-3-675B-Instruct-2512: VRAM & local deployment
675B total · 41B active (MoE) parameters. About 451 GB at 4-bit and 1.49 TB at BF16 with one 8K-token request.
released 2025-11-28licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Mistral AI · mistralai |
|---|---|
| Family / series | Mistral / Magistral / Devstral · Mistral-Large-3 |
| Type | Text LLM |
| Parameters | 675B total · 41B active (MoE) Source: official model card“41B active parameters and 675B total parameters” |
| Context length | 288K tokens (294,912)max_position_embeddings in config.json |
| Architecture | 61 layers · MLA · MoE |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-11-28 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 1.35 TB | 1.49 TB | 1.49 TB | 1.49 TB | 8 × B300 (2,304GB) | — |
| FP8 / INT8 / Q8_0 | 717 GB | 790 GB | 792 GB | 799 GB | 8 × H200 (1,128GB) | — |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 409 GB | 451 GB | 453 GB | 460 GB | 8 × H100 (640GB) | — |
KV cache per request: 8K 0.6 GB · 32K 2.3 GB · 128K 9.2 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
2 official repo(s) from mistralai.
- Mistral-Large-3-675B-Instruct-2512-NVFP4 Instruct/NVFP4
- Mistral-Large-3-675B-Instruct-2512 Instruct
05Other Mistral / Magistral / Devstral models
All 35 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| LIDstral-Arabic | — | — | 2026-10-08 |
| Voxtral-Mini-4B-Realtime-Arabic | 4.43B | 3.5 GB | 2026-10-08 |
| Shieldstral-1.0-3B | 3.85B | 3.9 GB | 2026-07-16 |
| Mistral-Medium-3.5-128B | 127.7B | 88.6 GB | 2026-03-31 |
| Mistral-Small-4-119B-2603 | 119B / 6.5B | 80.0 GB | 2026-01-23 |
| Voxtral-Mini-4B-Realtime-2602 | 4.43B | 3.5 GB | 2026-01-21 |
| Devstral-2-123B-Instruct-2512 | 125B | 86.8 GB | 2025-11-28 |
| Voxtral-4B-TTS-2603 | 4B | 3.2 GB | 2025-11-17 |
06Sources
Data checked 2026-07-15. Parameters, context and licence are copied from the official repository; memory figures are our estimates.