MI

mistralai.Mistral Large 3 675B Instruct 2512 BF16

MistralGGUF by DevQuasarUpdated 2025-12-06
Download on Hugging Face
Parameters673B
Context288K
Layers61
Architecturedeepseek2
Smallest quant244.8 GB
Quick answer

mistralai.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 6 quants, from 244.8 GB (Q2_K) to 715.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mistralai.Mistral Large 3 675B Instruct 2512 BF16 is a 673B-parameter Mistral model in GGUF format, quantized by DevQuasar. Its trained context length is 288K tokens. The repository has 6 quant files, from 244.8 GB (Q2_K) to 715.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K244.8 GB (16 parts) 246.4 GB
Too big Get file →
Q3_K_M320.2 GB (22 parts) 321.8 GB
Too big Get file →
Q4_K_M405.8 GB (29 parts) 407.3 GB
Too big Get file →
Q5_K_M477.0 GB (33 parts) 478.5 GB
Too big Get file →
Q6_K552.7 GB (35 parts) 554.3 GB
Too big Get file →
Q8_0715.7 GB (51 parts) 717.3 GB
Too big Get file →

What GPU do you need for mistralai.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 mistralai.Mistral Large 3 675B Instruct 2512 BF16 quant should you choose?

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

The Q8_0 file is 715.7 GB, about 1.8 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 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 byDevQuasar
FamilyMistral
Downloads (HF)221
Last updated2025-12-06

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

How much VRAM does mistralai.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 mistralai.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 mistralai.Mistral Large 3 675B Instruct 2512 BF16 GGUF?

It depends on the quant: Q2_K is 244.8 GB, Q3_K_M is 320.2 GB, Q4_K_M is 405.8 GB, Q5_K_M is 477.0 GB, Q6_K is 552.7 GB, Q8_0 is 715.7 GB.

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

The files are on Hugging Face in the DevQuasar/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.

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

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Mistral models

All Mistral →

Other large models

All large models →