No — not on this device
DeepSeek V4 Pro 1.6T-A49B at Q4_K_M needs 928.9 GB against 22.4 GB usable, and the shortfall of 906.5 GB is more than 256 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
Does not fit
8K context
Q4_K_M · 927.8 GB
MIT
Released 13 Aug 2026
New this month
Not in the Ollama library
The 0813 refresh of the V4 flagship. Included as the honest ceiling; a terabyte of weights at Q4.
The VRAM budget
weights 927.8 GB
Weights 927.8 GB
KV cache @ 8K 0.54 GB
Runtime overhead 0.6 GB
Over budget 906.5 GB past 22.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 1632.7 GB | 1633.9 GB | — | ~0.3 | −0.1% ppl | 1611.5 GB over |
| Q6_K | 1260.1 GB | 1261.2 GB | — | ~0.4 | −0.4% ppl | 1238.8 GB over |
| Q5_K_M | 1089.1 GB | 1090.3 GB | — | ~0.4 | −0.8% ppl | 1067.9 GB over |
| Q4_K_M | 927.8 GB | 928.9 GB | — | ~0.5 | −1.9% ppl | 906.5 GB over |
| Q3_K_M | 751.1 GB | 752.2 GB | — | ~0.6 | −5.4% ppl | 729.8 GB over |
| Q2_K | 643.5 GB | 644.6 GB | — | ~0.8 | −15% ppl | 622.2 GB over |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.
How to run it
$ llama-server \
-hf deepseek-ai/DeepSeek-V4-Pro-0813:Q4_K_M \
-c 8192 -ngl 1
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
01Download is 927.8 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.