Smaller alternatives
Models that need less memory than Magistral Small 2506 and score about as well or better.
Magistral Small 2506
Mistral AI · 23.6B · Dense
Magistral Small 2506 is a 23.6B model from Mistral AI with a 40K-token context. At Q4_K_M with an 8K context it needs about 14.9 GB; 20 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 | 0.6 GB | 14.3 GB |
| 8K | 1.3 GB | 14.9 GB |
| 32K | 5 GB | 18.6 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 Magistral Small 2506 grade A or S at Q4_K_M.
Can I run Magistral Small 2506 locally?
Can I run Magistral Small 2506 locally?
Yes, if your GPU or Mac has about 14.9 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 Magistral Small 2506 need?
About 14.9 GB at Q4_K_M with an 8K context and 24.9 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.