Smaller alternatives
Models that need less memory than DeepSeek V4 Pro 0813 and score about as well or better.
DeepSeek V4 Pro 0813
MoE
DeepSeek · 1.7T (49B active) · Mixture of experts
DeepSeek V4 Pro 0813 is a 1.7T model from DeepSeek with a 1M-token context. At Q4_K_M with an 8K context it needs about 886.8 GB; 1110 GB leaves room for longer chats.
Mixture of experts
Parameters: 1.7T · Active: 49B
All 1.7T parameters load into memory, but only 49B 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 | 0.5 GB | 886.4 GB |
| 8K | 1 GB | 886.8 GB |
| 32K | 3.8 GB | 889.7 GB |
| 128K | 15.3 GB | 901.1 GB |
| 256K | 30.5 GB | 916.4 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 V4 Pro 0813 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 V4 Pro 0813 locally?
Can I run DeepSeek V4 Pro 0813 locally?
Yes, if your GPU or Mac has about 886.8 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 DeepSeek V4 Pro 0813 need?
About 886.8 GB at Q4_K_M with an 8K context and 1,634.6 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.