MI

Mistral-Large-4-1T-A52B-DSpark

MistralGGUF by unslothUpdated 2026-10-29
Download on Hugging Face
Parameters1050B
Context1024K
Layers3
Architecturedflash
Smallest quant2.2 GB
Quick answer

Mistral-Large-4-1T-A52B-DSpark needs about 424.1 GB of memory at IQ3_XXS (a 423.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 2.2 GB (Q8_0) to 2098.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.2 GB.

Mistral‑Large‑4‑1‑T‑A52B‑DSpark – 1T‑parameter multimodal LLM

Mistral‑Large‑4‑1‑T‑A52B‑DSpark is a 1 trillion‑parameter, natively multimodal model with a 1,048,576‑token context window. It supports reasoning, tools, and vision. The model is quantized by unsloth and available in multiple GGUF formats.

Good at

  • Long‑context reasoning
  • Multimodal instruction following
  • Vision grounding

Limits

  • No vision without mmproj
  • Large memory for high‑precision quants
  • License is other

Best for

  • Enterprise analytics
  • Secure coding assistance
  • Legal document review

Who it’s for. Developers and researchers needing a large, multimodal model for complex reasoning tasks. The model is suitable for applications that require extended context and vision input.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_02.2 GB 2.8 GB
Fits Get file →
BF164.2 GB 4.8 GB
Fits Get file →
IQ1_S233.0 GB (6 parts) 233.6 GB
Too big Get file →
IQ1_M259.6 GB (7 parts) 260.1 GB
Too big Get file →
IQ2_XXS302.5 GB (8 parts) 303.0 GB
Too big Get file →
Q2_K_XL378.3 GB (9 parts) 378.8 GB
Too big Get file →
IQ3_XXS423.5 GB (10 parts) 424.1 GB
Too big Get file →
Q3_K_XL492.7 GB (12 parts) 493.3 GB
Too big Get file →
Q4_K_XL604.8 GB (14 parts) 605.3 GB
Too big Get file →
Q5_K_XL783.8 GB (18 parts) 784.3 GB
Too big Get file →
Q6_K_XL890.5 GB (20 parts) 891.0 GB
Too big Get file →
Q8_01115.2 GB (25 parts) 1115.7 GB
Too big Get file →
BF162098.9 GB (44 parts) 2099.4 GB
Too big Get file →

For 8 GB VRAM use Q8_0 (2.8 GB memory at 8 k context). For 16 GB VRAM use BF16 (4.8 GB). For 32 GB VRAM use Q2_K_XL (378.8 GB). Larger quants need correspondingly larger RAM.

What GPU do you need for Mistral-Large-4-1T-A52B-DSpark?

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 Q8_0 (2.2 GB file, about 2.8 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.8 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.8 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.8 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.8 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.8 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.8 GB in use).

Which Mistral-Large-4-1T-A52B-DSpark quant should you choose?

IQ3_XXS (423.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q8_0 at 2.2 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters1050B
Layers3
Trained context1,048,576 tokens
KV cache (fp16)6 KB per token

Source

Quantized byunsloth
FamilyMistral
Licenseother
Downloads (HF)5,291
Last updated2026-10-29

Frequently asked questions about Mistral-Large-4-1T-A52B-DSpark

How much VRAM does Mistral-Large-4-1T-A52B-DSpark need?

About 424.1 GB at IQ3_XXS with an 8K context window. That is the 423.5 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-4-1T-A52B-DSpark on an 8 GB GPU?

Yes, with BF16: the 4.2 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mistral-Large-4-1T-A52B-DSpark GGUF?

It depends on the quant: Q8_0 is 2.2 GB, BF16 is 4.2 GB, IQ1_S is 233.0 GB, IQ1_M is 259.6 GB, IQ2_XXS is 302.5 GB, Q2_K_XL is 378.3 GB and 7 more.

What context length does Mistral-Large-4-1T-A52B-DSpark support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.2 GB at 32K.

Where can I download Mistral-Large-4-1T-A52B-DSpark GGUF?

The files are on Hugging Face in the unsloth/Mistral-Large-4-1T-A52B-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-4-1T-A52B-DSpark use?

Hugging Face lists the license as other. 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 this model on 8 GB VRAM?

Yes, the Q8_0 quant uses 2.8 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support vision?

Yes, it includes a Pixtral‑style vision encoder; use the mmproj file for image input.

What is the maximum context length?

The model supports 1,048,576 tokens as its trained context length.

Other GGUFs of Mistral-Large-4-1T-A52B

Similar models

Browse all →

More from unsloth

All by unsloth →

More Mistral models

All Mistral →

Other large models

All large models →