# Mistral-Large-4-1T-A52B

> Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's…

- **Organisation:** mistralai
- **Category:** Vision-Language Models
- **Parameters:** 1T total, 52B active (MoE)
- **Context length:** 1,048,576 tokens
- **Licence:** Custom licence (Check licence)
- **Released:** 2026-09-30
- **Hugging Face:** 20.6K downloads (30 days), 1.7K likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 330.98 |
| Q3_K_M | 487.44 |
| Q4_K_M | 602.35 |
| Q5_K_M | 705.02 |
| Q6_K | 815.04 |
| Q8_0 | 1048.51 |
| F16 | 1965.28 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [Transformers](https://github.com/huggingface/transformers)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LM Studio](https://lmstudio.ai) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [MLX](https://github.com/ml-explore/mlx-lm) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's own datacenters in Europe.

Mistral Large 4 unifies instruction following, reasoning, coding, and agentic workflows in a single set of weights. While a generalist model, it shows especially good performance on workloads such as cybersecurity, finance, and law, and it surpasses frontier closed models on visual grounding. It is natively fluent in 160+ languages, including every official language of the European Union.

Find more information on our blog. The model is also served on the Mistral API as mistral-large-4.

Mistral Large 4 includes the following architectural choices:

• ~1T total / ~52B active parameters: granular Mixture-of-Experts with 128 routed experts (4 active per token) and 1 shared expert.
• 1M context length, for long-context workloads.
• Multimodal input: accepts text and image input, with text output. Pixtral-style vision encoder trained to handle variable image sizes and aspect ratios.
• Instruct and Reasoning functionalities with function calls, reasoning effort configurable per request.

Mistral Large 4 offers the following capabilities:

## Alternatives

- [thinkingmachines/Inkling](https://selfhost.directory/models/thinkingmachines/inkling) (952B (18.1B active), Apache 2.0, ≈567.17 GB at Q4): Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.
- [moonshotai/Kimi-K2.7-Code](https://selfhost.directory/models/moonshotai/kimi-k2.7-code) (1.03T (33.3B active), modified-mit, ≈632.16 GB at Q4): Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by…
- [deepseek-ai/DeepSeek-V4.1-Flash](https://selfhost.directory/models/deepseek-ai/deepseek-v4.1-flash) (763B (188B active), MIT, ≈453.59 GB at Q4): We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.
- [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://selfhost.directory/models/deepseek-ai/deepseek-v4.1-flash-1017) (763B (188B active), MIT, ≈453.59 GB at Q4): DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks.
- [moonshotai/Kimi-K2.6](https://selfhost.directory/models/moonshotai/kimi-k2.6) (1.03T (33.3B active), modified-mit, ≈632.16 GB at Q4): Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
- [moonshotai/Kimi-K2.5](https://selfhost.directory/models/moonshotai/kimi-k2.5) (1.03T (33.3B active), modified-mit, ≈632.16 GB at Q4): Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.

More: https://selfhost.directory/models/mistralai/mistral-large-4-1t-a52b/alternatives

## Similar size

- [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://selfhost.directory/models/deepseek-ai/deepseek-v4.1-flash-1017) (763B)
- [deepseek-ai/DeepSeek-V4.1-Flash](https://selfhost.directory/models/deepseek-ai/deepseek-v4.1-flash) (763B)
- [moonshotai/Kimi-K2.6](https://selfhost.directory/models/moonshotai/kimi-k2.6) (1.03T)
- [moonshotai/Kimi-K2.7-Code](https://selfhost.directory/models/moonshotai/kimi-k2.7-code) (1.03T)
- [moonshotai/Kimi-K2.5](https://selfhost.directory/models/moonshotai/kimi-k2.5) (1.03T)
- [thinkingmachines/Inkling](https://selfhost.directory/models/thinkingmachines/inkling) (952B)

## FAQ

**How much VRAM does Mistral-Large-4-1T-A52B need?**
About 602 GB at Q4_K_M with an 8K context. Q8_0 needs about 1049 GB and full precision about 1965 GB. Longer contexts need more memory for the KV cache.

**Can Mistral-Large-4-1T-A52B run on a consumer GPU?**
Not comfortably on a single one: it needs about 602 GB at Q4. Split it over several GPUs, use a large unified-memory machine, or offload part of it to system RAM.

**Can I use Mistral-Large-4-1T-A52B commercially?**
Unclear. It is released under Custom licence. Custom licence: read the model card before using it commercially. Check the licence on the model card before using it in a product.

**What is the context length of Mistral-Large-4-1T-A52B?**
1,048,576 tokens (1M). The full window needs far more memory than an 8K context.

**How do I run Mistral-Large-4-1T-A52B with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/unsloth/Mistral-Large-4-1T-A52B-GGUF:UD-Q4_K_XL. With llama.cpp: llama-server -hf unsloth/Mistral-Large-4-1T-A52B-GGUF:UD-Q4_K_XL, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/mistralai/Mistral-Large-4-1T-A52B
- homepage: https://mistral.ai/news/mistral-large-4-oss/
- github: https://github.com/mistralai/mistral-vibe

---
Source: https://selfhost.directory/models/mistralai/mistral-large-4-1t-a52b