Smaller alternatives
Models that need less memory than DeepSeek V3.1 and score about as well or better.
DeepSeek V3.1
MoE
DeepSeek · 684.5B (37B active) · Mixture of experts
DeepSeek V3.1 is a 684.5B model from DeepSeek with a 160K-token context. At Q4_K_M with an 8K context it needs about 378.4 GB; 474 GB leaves room for longer chats.
Mixture of experts
Parameters: 684.5B · Active: 37B
All 684.5B parameters load into memory, but only 37B work on each token, so it runs at the speed of a much smaller model.
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 | 0.3 GB | 378.1 GB |
| 8K | 0.5 GB | 378.4 GB |
| 32K | 2.1 GB | 380 GB |
| 128K | 8.6 GB | 386.4 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 DeepSeek V3.1 grade A or S at Q4_K_M.
No desktop device in our catalog runs it at grade A or better.
Can I run DeepSeek V3.1 locally?
Can I run DeepSeek V3.1 locally?
Yes, if your GPU or Mac has about 378.4 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 DeepSeek V3.1 need?
About 378.4 GB at Q4_K_M with an 8K context and 665.1 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.