Yes, just — 5.6 GB spare

DeepSeek-R1 671B at Q4_K_M fits your M3 Ultra · 512 GB entirely in unified memory at 8K context, at an estimated 10 tokens per second. Past 91K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully in unified memory 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.

The VRAM budget

weights 377.3 GB
Weights 377.3 GB KV cache @ 8K 0.54 GB Runtime overhead 0.6 GB Free 5.6 GB of 384.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 664.0 GB 665.1 GB — ~5.7 −0.1% ppl 281.1 GB over
Q6_K 512.4 GB 513.6 GB — ~7.4 −0.4% ppl 129.6 GB over
Q5_K_M 442.9 GB 444.0 GB — ~8.5 −0.8% ppl 60.0 GB over
Q4_K_M 377.3 GB 378.4 GB 91K 10 −1.9% ppl Recommended
Q3_K_M 305.4 GB 306.6 GB 128K 12 −5.4% ppl Long context
Q2_K 261.7 GB 262.8 GB 128K 14 −15% ppl Long context

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
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/DeepSeek-R1-4bit \
    --max-tokens 512 --prompt "Hello"

Apple's own array framework. The fastest path on Apple Silicon. More on MLX.

01Download is 377.3 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 384.0 GB of 512 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03Only 5.6 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 91K context.
See all models for this rig Compare with another model

Related models on an M3 Ultra · 512 GB

ModelTotalTok/s est.
DeepSeek-R1-Distill-Llama 70B
70.6B · same family
Q4_K_M · 42.8 GB 11 Runs great
DeepSeek-R1-Distill-Qwen 32B
32.8B · same family
Q4_K_M · 21.0 GB 24 Runs great
DeepSeek-R1-Distill-Qwen 14B
14.8B · same family
Q4_K_M · 10.4 GB 54 Runs great
DeepSeek-R1-Distill-Qwen 7B
7.62B · same family
Q4_K_M · 5.3 GB 104 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 23 Runs great

Every model against the M3 Ultra · 512 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 →