Welcome Le Chonk: Mistral Large 4 on Hugging Face Mistral released Mistral Large 4, nicknamed "Le Chonk," a multimodal Mixture-of-Experts model with roughly 1T total and 49B active parameters and a 1M-token context window, Hugging Face announced. The model ships in two official variants plus GGUFs built by Unsloth and the llama.cpp team, under the Mistral Ecosystem Open-Weight License, an MIT derivative that limits model-as-a-service offerings. Mistral reports Mistral Large 4 scores 82% on the Artificial Analysis Cyber Index, which asks a model to reproduce and then patch a real vulnerability in open-source software, while its average refusal rate on cyber prompts from JailbreakBench, StrongREJECT and AgentHarm exceeds that of any other open-weight model. Image-Text-to-Text • Updated • 278 • 1.01k https://huggingface.co/mistralai/Mistral-Large-4-1T-A52B "Welcome Le Chonk: Mistral Large 4 on Hugging Face" Update on GitHub https://github.com/huggingface/blog/blob/main/mistral-large4.md Mistral Large 4 aka Le Chonk is a multimodal, multilingual, Mixture-of-Experts MoE model from Mistral. It takes text and images as input and generates text. It has about 1T total, 49B active parameter , and a context window of 1M tokens . The model is released in two official variants: There are also GGUFs https://huggingface.co/ggml-org created by Unsloth https://huggingface.co/unsloth/Mistral-Large-4-1T-A52B-GGUF and the llama.cpp team. It’s distributed under the Mistral Ecosystem Open-Weight License an MIT derivative that establishes limitations for model-as-a-service offerings . Mistral Large 4 is particularly strong for cybersecurity, coding agents, and multimodality. In this post, we look at how the model works, its capabilities, architecture and more Table of Contents What is new with Mistral Large 4 Mistral Large 4 https://huggingface.co/collections/mistralai/mistral-large-4 combines a large pool of experts with sparse attention and a Pixtral https://huggingface.co/docs/transformers/en/model doc/pixtral vision encoder. The language model selects a small group of experts for each token, while its attention indexer selects which earlier token positions to attend to. These are two different forms of sparsity, where one selects feed-forward networks, the other selects context positions. You can find all the checkpoints in the Mistral Large 4 collection https://huggingface.co/collections/mistralai/mistral-large-4 . Cybersecurity Capabilities Mistral Large 4 scores 82% on the Artificial Analysis Cyber Index test that asks a model to reproduce a real vulnerability in open-source software and then patch the software. Mistral reports that several closed frontier models score near zero on the same test because they refuse to attempt the work. This is super important for defenders, because fixing a vulnerability usually requires reproducing the vulnerability. In Mistral’s internal testing, Mistral Large 4 was also useful for malware analysis, vulnerability prioritisation and writing detection rules, which the model was not explicitly trained for. Mistral mainly positions the model for defensive security work. Vulnerability research and incident response often appear like attacks in model input, so closed source filters can block them. A team that depends on an API can also lose access in the middle of an incident. Crucially, open weight models put both the usage policy and the deployment under the user’s control. That said, the model still declines harmful requests: on cyber prompts from JailbreakBench, StrongREJECT and AgentHarm, its average refusal rate is higher than any other open weight model. For community builders, an open weight model like Mistral Large 4 unlocks a load of downstream use cases. You could build your own cyber system around your code base, crash logs, and malware samples. For example, with TRL you could fine-tune fine-tuning-with-trl smaller models from Mistral Large 4 traces patching your code base. In fact, reproduce-then-patch tasks use a verifiable reward, so it fits with RL environments that could be used to further RL smaller security models. Open weights also let researchers measure the model’s refusal behaviour directly instead of relying on the provider’s description. In short, cyber capabilities like ML4’s in the open are a huge boost for the community. We have interviewed Pierre Stock about the cyber capabilities of the model, you can watch it here https://www.youtube.com/embed/FczbSauVvjw . Architecture Mistral Large 4’s text decoder has 72 layers, a hidden dimension of 6,144, and 64 attention heads. Its attention blocks combine Multi-head Latent Attention MLA with a DeepSeek Sparse Attention DSA indexer a direction in other models such as GLM 5.3 . MLA keeps a compressed KV representation, and DSA selects up to 2,048 key positions for each query. For each decoder block, there’s a 3:1 RoPE to NoPE pattern, i.e. 3 decoder layers employ RoPE and every fourth layer uses NoPE. The model also shares KV state across layers. The first decoder layer uses a dense feed-forward network. The other 71 layers use MoE blocks, in which a softmax router selects four of the 128 experts for each token. One shared expert always runs alongside the selected experts, for a total of 5 active experts per token. Regarding RoPE, Mistral uses LeRope , a YaRN-scaled RoPE with one learned multiplier per frequency. Vision encoder Mistral Large 4 employs a 1.6B Pixtral encoder. Pixtral has 30 layers, a hidden dimension of 2,048, and 16 attention heads. It uses 14 × 14 patches and a patch-merge projector with spatial merge size 2. You can see the encoder pipeline below. Benchmark Results Mistral Large 4 delivers strong benchmark performance across coding, cybersecurity, multimodal understanding, and agentic workflows, positioning it as a competitive addition to the open-weight ecosystem. As of October 29, 2026, the model is the fifth best open weights model on Artificial Analysis Intelligence index. On coding, ML4 achieves 61.7% on DeepSWE v1.1 , 59.4% on SWE-Atlas-QnA , and 28.3% on Terminal-Bench 4 . Its combined Coding Agent Index score of 49.8% places it ahead of DeepSeek V4 Pro 0813 and Qwen3.8 Max. Coding capabilities of ML4 extend to knowledge work, with 59.9% on AutomationBench and 1,393 Elo on AA-Briefcase , which evaluate business workflows and long-horizon professional tasks. Cybersecurity is one of Mistral Large 4’s standout capabilities, with strong results across real-world vulnerability assessment and security competition tasks. Three benchmarks highlight the model’s cyber performance: - Artificial Analysis Cyber Index: ML4 ranks among the top five models globally on this independent evaluation of models’ ability to find and fix software vulnerabilities. - Vulnerability reproduction and patching: It achieves 82% , the highest reported score on this test within the index. The task requires reproducing a real vulnerability in open-source software and then patching it, testing both investigation and remediation. - Cybench: ML4 solves 93% of a suite of 40 challenges drawn from security competitions , demonstrating strong performance on hands-on security problems. Mistral Large 4 also demonstrates 93.3% attack resistance on Lakera’s B3 benchmark , adding evidence of robustness against prompt-injection attacks. Beyond benchmarks, internal testing showed promising results in malware analysis, vulnerability prioritization, and detection-rule generation. Inference Support Mistral Large 4 is shipped with day-0 support for transformers, vLLM and llama.cpp. GGUF quants are available from GGUF and the llama.cpp team https://huggingface.co/ggml-org/Mistral-Large-4-1T-A52B-GGUF . We provide options to deploy remotely with Inference Endpoints, and use serverless inference through Inference Providers. Transformers The Transformers implementation provides AutoModelForMultimodalLM , with AutoProcessor preparing the conversation and image inputs. Mistral Large 4 can take low , medium , high as reasoning effort. The default is high , and note that reasoning cannot be disabled, so using reasoning effort : none would still use high . To run the model, upgrade the transformers package pip install --upgrade transformers python import os from transformers import AutoProcessor, AutoModelForMultimodalLM, DistributedConfig distributed config = DistributedConfig tp size=int os.environ "WORLD SIZE" , ep size=int os.environ "WORLD SIZE" , model id = "mistralai/Mistral-Large-4-1T-A52B" processor = AutoProcessor.from pretrained model id model = AutoModelForMultimodalLM.from pretrained model id, distributed config=distributed config, only text text messages = { "role": "user", "content": "Who are you?" } text + image multimodal messages = { "role": "user", "content": { "type": "image", "image": "https://huggingface.co/datasets/huggingface/cats-image/resolve/main/cats image.jpeg", }, { "type": "text", "text": "How many cats are in the image?", }, , }, for messages in text messages, multimodal messages : inputs = processor.apply chat template messages, add generation prompt=True, tokenize=True, return dict=True, return tensors="pt", reasoning effort="medium", .to model.device .to model.dtype input len = inputs "input ids" .shape -1 outputs = model.generate inputs, max new tokens=100 if int os.environ "RANK" == 0: print processor.decode outputs 0 input len: , skip special tokens=False You can run the script above by saving it in a python file script.py and then run torchrun --nproc-per-node 8 script.py vLLM vLLM supports the high-quality NVFP4 Mistral Large 4 checkpoint, which has a smaller memory footprint and requires NVIDIA Blackwell GPUs. The model also ships with a DSpark drafter for additional speed-ups with vLLM. Launch the server like this: vllm serve mistralai/Mistral-Large-4-1T-A52B-NVFP4 \ --config-format mistral \ --load-format mistral \ --tensor-parallel-size 8 \ --decode-context-parallel-size 8 \ --enable-expert-parallel \ --dtype bfloat16 \ --max-model-len 131072 \ --max-num-seqs 16 \ --max-num-batched-tokens 2048 \ --gpu-memory-utilization 0.85 \ --enable-prefix-caching \ --enforce-eager \ --mm processor cache gb 0.0 Once the server is up and running, you can run the following. curl -s http://127.0.0.1:8000/v1/chat/completions -H 'Content-Type: application/json' \ -d '{"messages": {"role":"user","content":"What is 17 23?"} ,"max tokens":512}' Llama.cpp Llama.cpp and Llama App https://llama.app/ already support Mistral Large 4. You can install Llama App with the following command: curl -LsSf https://llama.app/install.sh | sh Then you can start the server as follows, indicating the quant suffix after the model ID: llama serve -hf ggml-org/Mistral-Large-4-1T-A52B-GGUF:Q2 K Here’s the repository https://huggingface.co/ggml-org/Mistral-Large-4-1T-A52B-GGUF with the quants derived from the FP8 checkpoint, and this is the NVFP4 one https://huggingface.co/ggml-org/Mistral-Large-4-1T-A52B-NVFP4-GGUF , converted from the official NVFP4 repo. Once the server has started, you can head to localhost:9931 to chat using the built-in WebUI. From the web UI you can add images for inference and adjust the reasoning lever. You can also query the server as follows. Feel free to check out the API reference https://llama.app/docs/serve for multimodality, tool calls and more. curl http://localhost:8080/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "messages": {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Write a limerick about python exceptions"} }' You can run image-text inference as follows. curl -s http://127.0.0.1:8080/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer