No — not on this device

Qwen3 8B at Q4_K_M needs 6.3 GB against 5.4 GB usable, and the shortfall of 0.9 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 · 4.6 GB Apache 2.0 Released Apr 2025

Apache-2.0 alternative to Llama 3.1 8B, with a switchable thinking mode.

Hardware requirements What hardware do I need to run Qwen3 8B? →

At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

Fits instead: Qwen3 4B (4.0 GB) · Qwen3 1.7B (2.4 GB)

The VRAM budget

weights 4.6 GB
Weights 4.6 GB KV cache @ 8K 1.13 GB Runtime overhead 0.6 GB Over budget 0.9 GB past 5.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 15.3 GB 17.0 GB — ~3.7 Reference 11.6 GB over
Q8_0 8.1 GB 9.8 GB — ~6.9 −0.1% ppl 4.4 GB over
Q6_K 6.3 GB 8.0 GB — ~8.9 −0.4% ppl 2.6 GB over
Q5_K_M 5.4 GB 7.1 GB — ~10 −0.8% ppl 1.7 GB over
Q4_K_M 4.6 GB 6.3 GB 1K ~12 −1.9% ppl 0.9 GB over
Q3_K_M 3.7 GB 5.5 GB 7K ~15 −5.4% ppl 0.1 GB over
Q2_K 3.2 GB 4.9 GB 11K 17 −15% ppl Fits

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/Qwen3-8B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 4.6 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 5.4 GB of 8 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
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 an M3 · 8 GB

ModelTotalTok/s est.
Qwen3 14B
14.8B · same family
Q4_K_M · 10.2 GB — Won't fit
Qwen3 4B
4.02B · same family
Q4_K_M · 4.0 GB 25 Runs great
Qwen3 30B-A3B
30.5B MoE · same family
Q4_K_M · 18.5 GB — Won't fit
Qwen3 Coder 30B-A3B
30.5B MoE · same family
Q4_K_M · 18.5 GB — Won't fit
Fara 7B
8.29B · similar size
Q4_K_M · 5.7 GB — Won't fit
Llama 3.1 8B Instruct
8.03B · similar size
Q4_K_M · 6.1 GB — Won't fit
Gemma 4 E4B
8.0B · similar size
Q4_K_M · 5.2 GB 12 Tight fit

Every model against the M3 · 8 GB →

Qwen3 8B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
6.3 GB 34 Tight fit
Arc B570
8.8 GB usable · 380 GB/s
6.3 GB 50 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
6.3 GB 47 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
6.3 GB 15 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
6.3 GB 133 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
6.3 GB 126 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
6.3 GB 49 Runs great

All 114 devices, by tier →