No — not on this device

DeepSeek-R1 671B at Q4_K_M needs 378.4 GB against 96.0 GB usable, and the shortfall of 282.4 GB is more than 64 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 · 377.3 GB MIT Released Jan 2025

The January 2025 moment. Multi-head latent attention keeps its KV cache tiny; the weights do not.

Hardware requirements What hardware do I need to run DeepSeek-R1 671B? →

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.

Fits instead: DeepSeek-R1-Distill-Llama 70B (42.8 GB) · DeepSeek-R1-Distill-Qwen 32B (21.0 GB)

The VRAM budget

weights 377.3 GB
Weights 377.3 GB KV cache @ 8K 0.54 GB Runtime overhead 0.6 GB Over budget 282.4 GB past 96.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 664.0 GB 665.1 GB — ~1.9 −0.1% ppl 569.1 GB over
Q6_K 512.4 GB 513.6 GB — ~2.5 −0.4% ppl 417.6 GB over
Q5_K_M 442.9 GB 444.0 GB — ~2.9 −0.8% ppl 348.0 GB over
Q4_K_M 377.3 GB 378.4 GB — ~3.4 −1.9% ppl 282.4 GB over
Q3_K_M 305.4 GB 306.6 GB — ~4.2 −5.4% ppl 210.6 GB over
Q2_K 261.7 GB 262.8 GB — ~4.9 −15% ppl 166.8 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-R1:Q4_K_M \
    -c 8192 -ngl 15

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 377.3 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 96.0 GB of 128 GB as its share. Under Linux the GPU can usually address more than that, so treat the verdict as conservative.
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 DGX Spark · 128 GB

ModelTotalTok/s est.
DeepSeek-R1-Distill-Llama 70B
70.6B · same family
Q4_K_M · 42.8 GB 3.8 Runs great
DeepSeek-R1-Distill-Qwen 32B
32.8B · same family
Q4_K_M · 21.0 GB 8.3 Runs great
DeepSeek-R1-Distill-Qwen 14B
14.8B · same family
Q4_K_M · 10.4 GB 18 Runs great
DeepSeek-R1-Distill-Qwen 7B
7.62B · same family
Q4_K_M · 5.3 GB 36 Runs great
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
DeepSeek V4.1 Flash 552B-A16B
552B MoE · similar size
Q4_K_M · 311.0 GB — Won't fit

Every model against the DGX Spark · 128 GB →

DeepSeek-R1 671B on other hardware

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

All 114 devices, by tier →