Smaller alternatives
Models that need less memory than Mistral Medium 3.5 128B and score about as well or better.
Mistral Medium 3.5 128B
Vision
Mistral AI · 127.7B · Dense
Mistral Medium 3.5 128B is a 127.7B model from Mistral AI with a 256K-token context. At Q4_K_M with an 8K context it needs about 72.8 GB; 93 GB leaves room for longer chats.
Quantization options
| Quant | Bits | Memory | Quality | On your hardware |
|---|---|---|---|---|
| Q2_K | 3.16 | — | Noticeably worse | … |
| Q3_K_M | 4 | — | Some loss | … |
| Q4_K_M | 4.89 | — | Good | … |
| Q5_K_M | 5.7 | — | Good | … |
| Q6_K | 6.56 | — | Near original | … |
| Q8_0 | 8.5 | — | Near original | … |
| F16 | 16 | — | Original | … |
Memory by context length
At Q4_K_M. The context cache grows with every token the model keeps in mind.
| Context | Context cache | Total |
|---|---|---|
| 4K | 1.4 GB | 71.4 GB |
| 8K | 2.8 GB | 72.8 GB |
| 32K | 11 GB | 81.1 GB |
| 128K | 44 GB | 114.1 GB |
| 256K | 88 GB | 158.1 GB |
Next steps
Compare it with
Scored models of a similar size, side by side on your device.
Least hardware that runs it well
Desktop devices with the least memory that give Mistral Medium 3.5 128B grade A or S at Q4_K_M.
No desktop device in our catalog runs it at grade A or better.
Can I run Mistral Medium 3.5 128B locally?
Can I run Mistral Medium 3.5 128B locally?
Yes, if your GPU or Mac has about 72.8 GB free for it at Q4_K_M. Open this page on that computer to see the grade for your exact hardware, then start it with llama.cpp, Ollama or LM Studio.
How much memory does Mistral Medium 3.5 128B need?
About 72.8 GB at Q4_K_M with an 8K context and 126.8 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.