ModelTape
All modelsNew releasesRankingsRuns on my GPUOpen the app →
ModelTape / Models / Mistral Large 4
Mistral · open-weights

Mistral Large 4

Mistral Large 4 is an open-weights language model from Mistral, released October 6, 2026. Its makers disclosed about 1.1T parameters. The context window is 1M tokens. On the Epoch Capabilities Index it scores 154.6, rank 48 of 256 rated models. API price: $0.7 input / $2.1 output per million tokens.

Today, we’re launching a public preview of Mistral Large 4. Unofficially ML4, very officially: le Chonk. ML4 pushes the frontier of open-weight performance. You can try the preview API today on Mistral Studio. Weights drop end of this month.

Check it against your own PC →

Lab
Mistral
Released
October 6, 2026
Weights
Open restricted use
Parameters
1.1T disclosed
Context
1M
Price / M tokens
$0.7 / $2.1 in / out
Epoch ECI
154.6 #48

Can you run Mistral Large 4 locally?

Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.

GPU memoryVerdictBest quantVRAMRAMtok/s
6 GB VRAMSize unknown––––
8 GB VRAMSize unknown––––
12 GB VRAMSize unknown––––
16 GB VRAMSize unknown––––
24 GB VRAMSize unknown––––
32 GB VRAMSize unknown––––

Parameter count unknown. The weights may not be on Hugging Face yet.

Strengths by category

ModelTape's 0–100 fit on Epoch AI benchmark results.

CategoryScoreBased on
Reasoning15.0Chess Puzzles, Mystery Game Puzzles
Knowledge67.7GPQA diamond, SimpleQA Verified

Benchmark results

Benchmark (Epoch AI)Score
OTIS Mock AIME99.4%
GPQA Diamond90.5%
Chess Puzzles25.3%
SimpleQA Verified22.4%
EBR-bench18.1%
Mystery Game Puzzles11.9%
Furniture Assembly1.2%

Links

Announcement · Epoch AI benchmarks

Models with a similar score

Kimi K3 · Gemini 3.7 Flash · Muse Spark 1.3 · GPT-5.4 · Grok 4.6 · Qwen 3.8 Max · Claude Opus 4.7 · GPT-5.2 Pro

More from Mistral

Mistral Large 4 Preview · Mistral Large 4 1T A52B · Leanstral 1.5 · Mistral Medium 3.5 · Mistral Small 4 · Devstral Small 2 · Devstral 2 · Ministral 3 3B

Data updated Thu, 12 Nov 2026 09:42 UTC. Benchmarks, Capabilities Index and model announcements: Epoch AI, “Capabilities & benchmarking” and “Data on AI models” (CC BY 4.0); category scores are ModelTape's own fit on Epoch's results. Releases and prices: models.dev (MIT). Sizes and quantizations: Hugging Face. “Runs on” figures are estimates from model size, quantization and memory bandwidth (±30–50%).
Live app · All models · New releases · Rankings · 6 GB · 8 GB · 12 GB · 16 GB · 24 GB · 32 GB · Legal notice (Impressum) · Privacy