Mistral Large 4 1T A52B
1000B total, 52B active · 1024k context · Mistral Ecosystem Open-Weight License · released 2026-09-30
chatcodingagenticvisionreasoning
Cheapest way to run it in Germany today
Nothing in stock in Germany today runs Mistral Large 4 1T A52B fully in memory at 128k context at 15 tok/s or more. A shorter context needs less memory; the table below shows what comes closest.
What to run it on in Germany
Fully in memory at 128k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Commercial use is allowed, but operating a Model-as-a-Service business requires a separate commercial license from Mistral. The card's examples serve it with tensor-parallel size 8, and an NVFP4 checkpoint is available for Blackwell GPUs. Parameter count taken from the model name. Sparse or compressed attention: KV read per token is estimated as full attention.
Questions
- What licence is Mistral Large 4 1T A52B released under?
- Mistral Ecosystem Open-Weight License.