Mistral-Large-4-1T-A52B The 1-trillion-parameter Mistral Large 4 for Ollama — 52B active · MLA + sparse attention · vision · 1M context

Mistral Ecosystem Open-Weight License · 2 tags · 236 / 496 GB · 256 GB or 512 GB machine · vision bundled · reasoning

Website · Model Catalog · Hugging Face · GitHub · Discord · X

🛡️ New from Orca — OrcaCyber Zero 1.5

Post-trained for cybersecurity: vulnerability analysis, vulnerability reproduction, red teaming & offensive-security research. 98.01% pass@1 on CyberGym Level 1 · 1M context · function calling · OpenAI-compatible API.

Try it on OrcaRouter →

🔌 New from Orca — Orca Connect

Running this in Ollama on your own machine? Orca Connect puts the rig under your desk behind your usual OrcaRouter API key, next to 200+ hosted models, reachable from a laptop, a phone or a cloud agent. Outbound only: no port forwarding, no tunnel, no firewall rule. Requests your own hardware serves cost $0, and orca-connect claude points Claude Code at your rig for one session.

Connect your rig → · ▶ Watch the demo

The full Mistral Large 4, run locally.

These are Ollama builds of Mistral-Large-4-1T-A52B. It is a 1T-parameter MoE with 128 routed experts (top-4) and one shared expert, 52B active per token. It uses MLA attention, DeepSeek-style sparse attention (top-2048) and a 1M-token context.

Routed experts are 98% of the weights, so that is where the bits were spent. Each group of expert layers got its own precision from measured KL divergence, not from a hand-set rule.

At the same file size, both builds sit closer to the original than unsloth’s UD-IQ1_S and UD-Q3_K_XL: 20% lower KLD at 233 GB, 13% lower at 492 GB, on held-out text the search never saw.

Vision included. Every tag carries the vision projector for image input. Mistral’s DSpark speculative-decoding drafter is in the GGUF repo for llama.cpp; Ollama does not run it.

Pick a tag

• Mix-512G fits a 512 GB machine. That covers a 512 GB Mac, a 512 GB server running on CPU, or 4 × H200. It is close to the original: 97% of next tokens match, and perplexity is 0.75% higher.
• Mix-256G fits a 256 GB machine. That covers a 256 GB Mac, a 256 GB PC on CPU, or 2 × H200. It averages under 2 bits per expert weight, which costs quality: 92% of next tokens match, and perplexity is 8.7% higher.

Use Mix-512G if you have the memory. Use Mix-256G to run the full model on half of it.

Usage (Ollama)

Requires Ollama v0.40.16 or later.

ollama run orcarouter/Mistral-Large-4-1T-A52B            # Mix-256G
ollama run orcarouter/Mistral-Large-4-1T-A52B:mix-512g

cURL

curl http://localhost:11434/api/chat -d '{
  "model": "orcarouter/Mistral-Large-4-1T-A52B",
  "messages": [{"role": "user", "content": "Hello!"}]
}'

Python

from ollama import chat
resp = chat(
    model="orcarouter/Mistral-Large-4-1T-A52B",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp["message"]["content"])

Image input

ollama run orcarouter/Mistral-Large-4-1T-A52B "What is in this image? ./photo.png"

• Reasoning is always on, and "think": false does not turn it off. The reasoning comes back in message.thinking, the answer in message.content.
• Images go in the images field of a message, or as a file path in the prompt with ollama run.
• No DSpark. The Ollama builds don’t include the draft model, so generation runs at plain-decoding speed.
• Mix-256G was run in Ollama (chat, reasoning and an image). Mix-512G was built the same way but not run there.

Evaluation

All builds are scored against a Q8_0 GGUF of the official FP8 checkpoint, using llama.cpp’s full-vocabulary KLD.

The text is Mistral Large 4’s own answers. Prompts come from four sources: - English chat (UltraChat 200k) - non-English chat (WildChat) - code (Magicoder OSS-Instruct) - math reasoning (OpenR1-Math)

The Q8_0 model answered each one, sampled as the model card recommends (temperature 1.0, top_p 0.95), with reasoning effort drawn per prompt from low / medium / high. Each conversation was rendered through the chat template with its reasoning as a [THINK] block. KLD is counted on the assistant tokens, reasoning and answer, over 64 windows of 2048 tokens. Truncated answers were dropped. The precision search used a separate draw and never saw this text.

Each build is compared with unsloth’s dynamic GGUF of the same size, from unsloth/Mistral-Large-4-1T-A52B-GGUF. Their published files were downloaded and scored with the same text, teacher and llama.cpp build.

At the same size, Mix-256G has 20% less KL divergence than UD-IQ1_S, and Mix-512G has 13% less than UD-Q3_K_XL. Both are also a little smaller, and both win in the tail (KLD p99).

Why the model’s own text. Mistral Large 4 always reasons before it answers. On other models’ answers (no reasoning block, someone else’s style) it makes confident misses on ~3% of tokens even at Q8_0, and which of those misses a quant happens to flip dominated the KLD. The same applies to the user turns, which are human-written. So the score covers what the model itself writes.

Method note. These are full-vocabulary KLD and next-token agreement at 2k context, not a downstream benchmark.

Model details

Bias, risks, and limitations

• Mix-256G is noticeably degraded. Under 2 bits per expert weight is a large cut for any model. It is the best we found at this size, not a match for the original.
• Tested on CUDA only. CPU and Apple Metal have not been run with these files yet.
• Vision was checked on a few images, not benchmarked. Long-context behaviour was not tested: all measurements are at 2k context or on short chats.
• Inherits the biases and limitations of Mistral-Large-4-1T-A52B.
• Requires llama.cpp with PR #31376 (master 78feec0 or later). Tools built on older llama.cpp, such as older Ollama and LM Studio releases, will not load these files. Ollama v0.40.16 and later do.

License

The Mistral Ecosystem Open-Weight License, inherited from the base model mistralai/Mistral-Large-4-1T-A52B. It is a modified MIT license that allows commercial and non-commercial use. Operating a Model-as-a-Service business with the model requires a separate commercial license from Mistral. See the license for the terms.

Elsewhere

• GGUF files, method and full evaluation: orcarouter/Mistral-Large-4-1T-A52B-GGUF

One Gateway. Every Model.

Route Smarter · Ship Safer · Spend Less

Website · Models · GitHub · Discord · X