No — not on this device

DeepSeek V4 Pro 1.6T-A49B at Q4_K_M needs 928.9 GB against 48.0 GB usable, and the shortfall of 880.9 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 Not in the Ollama library

The 0813 refresh of the V4 flagship. Included as the honest ceiling; a terabyte of weights at Q4.

Hardware requirements What hardware do I need to run DeepSeek V4 Pro 1.6T-A49B? →

No single GPU or Mac in the catalogue holds it at Q4_K_M — the page says what comes closest. Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 927.8 GB
Weights 927.8 GB KV cache @ 8K 0.54 GB Runtime overhead 0.6 GB Over budget 880.9 GB past 48.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 1632.7 GB 1633.9 GB — ~1.4 −0.1% ppl 1585.9 GB over
Q6_K 1260.1 GB 1261.2 GB — ~1.8 −0.4% ppl 1213.2 GB over
Q5_K_M 1089.1 GB 1090.3 GB — ~2.1 −0.8% ppl 1042.3 GB over
Q4_K_M 927.8 GB 928.9 GB — ~2.4 −1.9% ppl 880.9 GB over
Q3_K_M 751.1 GB 752.2 GB — ~3.0 −5.4% ppl 704.2 GB over
Q2_K 643.5 GB 644.6 GB — ~3.5 −15% ppl 596.6 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

terminal
$ llama-server \
    -hf deepseek-ai/DeepSeek-V4-Pro-0813:Q4_K_M \
    -c 8192 -ngl 3

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.
02The GPU shares one pool with the operating system, and these numbers count about 48.0 GB of 64 GB as its share. On Windows the firmware sets the split; on Linux the kernel’s GTT limit does, and can be raised.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model

Related models on a Ryzen AI Max+ 395 · 64 GB

ModelTotalTok/s est.
DeepSeek V4.1 Flash 552B-A16B
552B MoE · same family
Q4_K_M · 311.0 GB — Won't fit
DeepSeek V4 Flash 284B-A13B
284B MoE · same family
Q4_K_M · 160.7 GB — Won't fit
Qwen3.8 2.4T-A95B
2446B MoE · similar size
Q4_K_M · 1376.7 GB — Won't fit
Kimi K2.6 1T-A32B
1027B MoE · similar size
Q4_K_M · 578.6 GB — Won't fit
Kimi K3 2.8T-A104B
2780B MoE · similar size
Q4_K_M · 1564.0 GB — Won't fit
GLM-5.2 744B-A40B
753B MoE · similar size
Q4_K_M · 424.7 GB — Won't fit
GLM-5.3 744B-A40B
753B MoE · similar size
Q4_K_M · 424.7 GB — Won't fit

Every model against the Ryzen AI Max+ 395 · 64 GB →

DeepSeek V4 Pro 1.6T-A49B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
928.9 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
928.9 GB — Won't fit
M4 · 16 GB
10.7 GB usable · 120 GB/s
928.9 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
928.9 GB — Won't fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
928.9 GB — Won't fit
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
928.9 GB — Won't fit

All 114 devices, by tier →