Mistral AI
Mistral AI
Multimodal model · France ·May 2026

Mistral Medium 3.5

Multimodal Open (Restricted)
128B
Parameters
256K
Context
1
Benchmarks

About Mistral Medium 3.5

Mistral Medium 3.5 is an AI model developed by Mistral AI, in the multimodal category, released in 2026, made available as an open-weights model with 128B params. Mistral Medium 3.5 is a 128-billion-parameter dense model that folds chat, reasoning, and code into a single product wit.

On this page you'll find Mistral Medium 3.5's full specifications, including a context window of 256K tokens, 1 benchmark result. Review provider pricing and benchmark scores below, or compare Mistral Medium 3.5 head-to-head with other multimodal models.

→ More models by Mistral AI → All multimodal models → AI benchmarks leaderboard

Run Mistral Medium 3.5 locally — what to buy

Share this build ↗

Sized to what Mistral Medium 3.5 actually needs (~256k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
AMD Ryzen AI Max+ 395
Consumer GPU · ~$1,999
~2.8 tok/s
Q4 · fits full context · up to 128k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
Apple M2 Max 96GB
Apple · ~$3,300
~4.6 tok/s
Q4 · fits full context · up to 40k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
Apple M1 Ultra 128GB
Apple · ~$4,800
~9.2 tok/s
Q4 · fits full context · up to 128k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
2.8–3.3 tok/s
2 options →
Apple
4.6–9.2 tok/s
5 options →
Datacenter GPU
21.8–97.1 tok/s
6 options →

Community

Would you run Mistral Medium 3.5 again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Mistral Medium 3.5 benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
SWE-bench Verified code 77.6%

More models like Mistral Medium 3.5

AI
NeuroChess
· 72.3K
 Mistral AI
Mistral OCR 4
Mistral AI
 Mistral AI
Voxtral TTS
Mistral AI
 Mistral AI
Mistral Small 4
Mistral AI · 119B
 Mistral AI
Devstral Small 2
Mistral AI
 Mistral AI
Ministral 3 8B
Mistral AI

Frequently asked questions

What is Mistral Medium 3.5? ▶

Mistral Medium 3.5 is a 128-billion-parameter dense model that folds chat, reasoning, and code into a single product wit It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Mistral Medium 3.5? ▶

Mistral Medium 3.5 was developed by Mistral AI and released in 2026.

Is Mistral Medium 3.5 open source or proprietary? ▶

Mistral Medium 3.5 ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

What is Mistral Medium 3.5's context window? ▶

Mistral Medium 3.5 supports a context window of 256K tokens, and has 128B params.

How much does Mistral Medium 3.5 cost? ▶

Pricing for Mistral Medium 3.5 depends on the provider. See the providers table on this page for the latest API rates.

How does Mistral Medium 3.5 perform on benchmarks? ▶

Mistral Medium 3.5 is benchmarked across 1 evaluation on GenAIList, including SWE-bench Verified (77.6%). See the full benchmark table below and compare it with other models.

Mistral Medium 3.5 128B: Built for Long Stretches on Coding
Mistral AI Just Changed Everything (Medium 3.5 Review)
Mistral Medium 3.5 BEATS Kimi AND Claude? Local AI TEST & REVIEW
Mistral Medium 3.5 First Test

Know a great video about Mistral Medium 3.5?