Yes — with 190.2 GB to spare

Qwen3 0.6B at Q4_K_M fits your M3 Ultra · 256 GB entirely in unified memory at 8K context, at an estimated 1325 tokens per second. There is room for its full 32K window.

Fully in unified memory 8K context Q4_K_M · 0.3 GB Apache 2.0 Released Apr 2025

Useful mostly as a speculative-decoding draft model for its larger siblings.

Hardware requirements What hardware do I need to run Qwen3 0.6B? →

At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 0.3 GB
Weights 0.3 GB KV cache @ 8K 0.88 GB Runtime overhead 0.6 GB Free 190.2 GB of 192.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 1.1 GB 2.6 GB 32K 400 Reference Long context
Q8_0 0.6 GB 2.1 GB 32K 753 −0.1% ppl Long context
Q6_K 0.5 GB 1.9 GB 32K 976 −0.4% ppl Long context
Q5_K_M 0.4 GB 1.9 GB 32K 1129 −0.8% ppl Long context
Q4_K_M 0.3 GB 1.8 GB 32K 1325 −1.9% ppl Recommended
Q3_K_M 0.3 GB 1.7 GB 32K 1637 −5.4% ppl Long context
Q2_K 0.2 GB 1.7 GB 32K 1910 −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.

How to run it

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3-0.6B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 0.3 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 192.0 GB of 256 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 32K context on this card.
See all models for this rig Compare with another model

Related models on an M3 Ultra · 256 GB

ModelTotalTok/s est.
Qwen3 1.7B
1.72B · same family
Q4_K_M · 2.4 GB 462 Runs great
Qwen3 4B
4.02B · same family
Q4_K_M · 4.0 GB 198 Runs great
Qwen3 8B
8.19B · same family
Q4_K_M · 6.3 GB 97 Runs great
Qwen3 14B
14.8B · same family
Q4_K_M · 10.2 GB 54 Runs great
Qwen3.5 0.8B
0.87B · similar size
Q4_K_M · 1.2 GB 914 Runs great
Gemma 3 1B
1.0B · similar size
Q4_K_M · 1.2 GB 795 Runs great
Llama 3.2 1B Instruct
1.24B · similar size
Q4_K_M · 1.5 GB 641 Runs great

Every model against the M3 Ultra · 256 GB →

Qwen3 0.6B on other hardware

DeviceTotalTok/s est.
GeForce RTX 3060 Laptop
5.3 GB usable · 336 GB/s
1.8 GB 603 Runs great
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
1.8 GB 459 Runs great
M3 · 8 GB
5.4 GB usable · 100 GB/s
1.8 GB 166 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
1.8 GB 646 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
1.8 GB 199 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
1.8 GB 1809 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
1.8 GB 1723 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
1.8 GB 663 Runs great

All 114 devices, by tier →