MI

Mistral Large 3 675B Instruct 2512

MistralGGUF by bartowskiUpdated 2025-12-07
Download on Hugging Face
Parameters673B
Context288K
Layers61
Architecturedeepseek2
Smallest quant0.6 GB
Quick answer

Mistral Large 3 675B Instruct 2512 needs about 412.9 GB of memory at Q4_K_M (a 411.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.6 GB to 1347.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mistral Large 3 675B Instruct 2512 – a multimodal, granular Mixture‑of‑Experts model

Mistral Large 3 675B Instruct 2512 is a 673B parameter model with 41B active parameters. It supports vision, multilingual text, and agentic function calling. The model is trained for long‑context comprehension with a 256k token window.

Good at

  • Long‑context reasoning
  • Vision‑enabled text analysis
  • Agentic tool use

Limits

  • Requires large VRAM for full precision
  • No native GPU acceleration beyond llama.cpp
  • License is Apache‑2.0

Best for

  • Enterprise knowledge work
  • Complex document understanding
  • AI assistant with tool integration

Who it’s for. Developers and enterprises needing a high‑capacity, multimodal LLM for production workloads. The model is suitable for on‑premises deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.6 GB 2.2 GB
Fits Get file →
IQ1_S142.3 GB (4 parts) 143.9 GB
Too big Get file →
IQ1_M148.5 GB (4 parts) 150.1 GB
Too big Get file →
IQ2_XXS165.2 GB (5 parts) 166.7 GB
Too big Get file →
IQ2_XS189.5 GB (5 parts) 191.1 GB
Too big Get file →
IQ2_S190.8 GB (5 parts) 192.4 GB
Too big Get file →
IQ2_M216.2 GB (6 parts) 217.8 GB
Too big Get file →
Q2_K239.8 GB (7 parts) 241.4 GB
Too big Get file →
Q2_K_L240.7 GB (7 parts) 242.3 GB
Too big Get file →
IQ3_XXS269.6 GB (7 parts) 271.2 GB
Too big Get file →
IQ3_XS279.1 GB (8 parts) 280.7 GB
Too big Get file →
Q3_K_S295.3 GB (8 parts) 296.9 GB
Too big Get file →
IQ3_M309.9 GB (8 parts) 311.4 GB
Too big Get file →
Q3_K_M309.9 GB (8 parts) 311.5 GB
Too big Get file →
Q3_K_L321.7 GB (9 parts) 323.3 GB
Too big Get file →
Q3_K_XL322.5 GB (9 parts) 324.1 GB
Too big Get file →
IQ4_XS362.0 GB (10 parts) 363.5 GB
Too big Get file →
IQ4_NL382.4 GB (10 parts) 384.0 GB
Too big Get file →
Q4_0388.4 GB (10 parts) 390.0 GB
Too big Get file →
Q4_K_S396.1 GB (11 parts) 397.7 GB
Too big Get file →
Q4_K_M411.4 GB (11 parts) 412.9 GB
Too big Get file →
Q4_1423.0 GB (11 parts) 424.6 GB
Too big Get file →
Q5_K_M480.8 GB (13 parts) 482.4 GB
Too big Get file →
Q6_K554.9 GB (15 parts) 556.5 GB
Too big Get file →
Q8_0715.7 GB (20 parts) 717.3 GB
Too big Get file →
BF161347.0 GB (36 parts) 1348.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (file size 388.39 GB, memory ~390 GB at 8k context). For 16 GB VRAM, Q4_K_M or Q4_K_L (411.35 GB or 240.74 GB). For 32 GB VRAM, Q3_K_M or Q3_K_L (309.9 GB or 321.68 GB). Estimates are approximate.

What GPU do you need for Mistral Large 3 675B Instruct 2512?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 2.2 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 2.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 2.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 2.2 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 2.2 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 2.2 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 2.2 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 2.2 GB in use).

Which Mistral Large 3 675B Instruct 2512 quant should you choose?

Q4_K_M is the usual starting point for Mistral Large 3 675B Instruct 2512: it balances file size and quality well. Here it is a 411.4 GB file.

The Q8_0 file is 715.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.6 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters673B (approximate, mixture of experts)
Layers61
Trained context294,912 tokens
KV cache (fp16)130 KB per token

Source

Quantized bybartowski
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,386
Last updated2025-12-07

Frequently asked questions about Mistral Large 3 675B Instruct 2512

How much VRAM does Mistral Large 3 675B Instruct 2512 need?

About 412.9 GB at Q4_K_M with an 8K context window. That is the 411.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Mistral Large 3 675B Instruct 2512 on an 8 GB GPU?

Yes, with the smaller files: the 0.6 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mistral Large 3 675B Instruct 2512 GGUF?

It depends on the quant: file is 0.6 GB, IQ1_S is 142.3 GB, IQ1_M is 148.5 GB, IQ2_XXS is 165.2 GB, IQ2_XS is 189.5 GB, IQ2_S is 190.8 GB and 20 more.

What context length does Mistral Large 3 675B Instruct 2512 support?

The GGUF header lists a trained context length of 294,912 tokens (288K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Mistral Large 3 675B Instruct 2512 GGUF?

The files are on Hugging Face in the bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mistral Large 3 675B Instruct 2512 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Mistral Large 3 on 8 GB VRAM?

Only with a very low‑precision quant like Q4_0, which still requires ~390 GB of VRAM at 8k context. 8 GB VRAM is insufficient.

Does the model support vision?

Yes, it includes a 2.5B vision encoder for image analysis.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing commercial use.

Other GGUFs of Mistral-Large-3-675B-Instruct-2512

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other large models

All large models →