MI

Mistral Large 3 675B Instruct 2512 BF16

MistralGGUF by mradermacherUpdated 2026-10-27
Download on Hugging Face
Parameters673B
Context288K
Layers61
Architecturedeepseek2
Smallest quant244.8 GB
Quick answer

Mistral Large 3 675B Instruct 2512 BF16 needs about 407.3 GB of memory at Q4_K_M (a 405.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 9 quants, from 244.8 GB (Q2_K) to 477.0 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mistral Large 3 675B Instruct 2512 in GGUF format

Mistral Large 3 675B Instruct 2512 is a 673B parameter model with 39B active parameters. It supports a 256k context window and includes vision and multilingual capabilities. The model is released under Apache 2.0.

Good at

  • Vision analysis
  • Multilingual instruction
  • Agentic function calling

Limits

  • Large VRAM requirement
  • No native vision support in GGUF
  • Requires 256k context for full capability

Best for

  • Enterprise chat assistants
  • Retrieval‑augmented systems
  • Scientific workload integration

Who it’s for. Developers building production‑grade assistants or enterprise workflows that need a large context window and multimodal support. The model is suitable for on‑premises deployment with high‑end GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K244.8 GB 246.4 GB
Too big Get file →
Q3_K_S290.0 GB 291.6 GB
Too big Get file →
Q3_K_M320.2 GB 321.8 GB
Too big Get file →
Q3_K_L348.6 GB 350.2 GB
Too big Get file →
IQ4_XS360.7 GB 362.2 GB
Too big Get file →
Q4_K_S381.2 GB 382.8 GB
Too big Get file →
Q4_K_M405.8 GB 407.3 GB
Too big Get file →
Q5_K_S463.3 GB 464.9 GB
Too big Get file →
Q5_K_M477.0 GB 478.5 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 244.83 GB, estimated memory 246.4 GB). For 16 GB VRAM, Q3_K_S (290 GB, 291.6 GB). For 32 GB VRAM, Q4_K_S (381.24 GB, 382.8 GB). Estimates are approximate.

What GPU do you need for Mistral Large 3 675B Instruct 2512 BF16?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Mistral Large 3 675B Instruct 2512 BF16 quant should you choose?

Q4_K_M is the usual starting point for Mistral Large 3 675B Instruct 2512 BF16: it balances file size and quality well. Here it is a 405.8 GB file.

If memory is tight, the smallest file is Q2_K at 244.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)630
Last updated2026-10-27

Frequently asked questions about Mistral Large 3 675B Instruct 2512 BF16

How much VRAM does Mistral Large 3 675B Instruct 2512 BF16 need?

About 407.3 GB at Q4_K_M with an 8K context window. That is the 405.8 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 BF16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 246.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Large 3 675B Instruct 2512 BF16 GGUF?

It depends on the quant: Q2_K is 244.8 GB, Q3_K_S is 290.0 GB, Q3_K_M is 320.2 GB, Q3_K_L is 348.6 GB, IQ4_XS is 360.7 GB, Q4_K_S is 381.2 GB and 3 more.

What context length does Mistral Large 3 675B Instruct 2512 BF16 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 BF16 GGUF?

The files are on Hugging Face in the mradermacher/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 BF16 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 675B Instruct 2512 on 8 GB VRAM?

No, the smallest quant requires 246.4 GB of VRAM at 8k context. 8 GB VRAM is insufficient.

Does the GGUF version support vision?

The GGUF files do not include vision support; the model’s vision encoder is not part of the quantized files.

What license applies to the GGUF files?

The files are released under Apache 2.0, allowing commercial and non‑commercial use.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →