Yes — with 22.8 GB to spare

Qwen3.5 0.8B at Q4_K_M fits your M4 · 32 GB entirely in unified memory at 8K context, at an estimated 137 tokens per second. There is room for its full 256K window.

Fully in unified memory 8K context Q4_K_M · 0.5 GB Apache 2.0 Released 28 Feb 2026

Draft model for speculative decoding, or a classifier that fits in 1 GB.

Hardware requirements What hardware do I need to run Qwen3.5 0.8B? →

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 0.5 GB
Weights 0.5 GB KV cache @ 8K 0.09 GB Runtime overhead 0.6 GB Free 22.8 GB of 24.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 1.6 GB 2.3 GB 256K 41 Reference Long context
Q8_0 0.9 GB 1.6 GB 256K 78 −0.1% ppl Long context
Q6_K 0.7 GB 1.4 GB 256K 101 −0.4% ppl Long context
Q5_K_M 0.6 GB 1.3 GB 256K 117 −0.8% ppl Long context
Q4_K_M 0.5 GB 1.2 GB 256K 137 −1.9% ppl Recommended
Q3_K_M 0.4 GB 1.1 GB 256K 169 −5.4% ppl Long context
Q2_K 0.3 GB 1.0 GB 256K 198 −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. Only 6 of its 24 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.

How to run it

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3.5-0.8B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 0.5 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 24.0 GB of 32 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 256K context on this card.
See all models for this rig Compare with another model

Related models on an M4 · 32 GB

ModelTotalTok/s est.
Qwen3.5 2B
2.27B · same family
Q4_K_M · 2.0 GB 53 Runs great
Qwen3.5 4B
4.66B · same family
Q4_K_M · 3.5 GB 26 Runs great
Qwen3.5 9B
9.65B · same family
Q4_K_M · 6.3 GB 12 Runs great
Qwen3.5 122B-A10B
125B MoE · same family
Q4_K_M · 71.1 GB — Won't fit
Gemma 3 1B
1.0B · similar size
Q4_K_M · 1.2 GB 119 Runs great
Llama 3.2 1B Instruct
1.24B · similar size
Q4_K_M · 1.5 GB 96 Runs great
Qwen3 0.6B
0.6B · similar size
Q4_K_M · 1.8 GB 199 Runs great

Every model against the M4 · 32 GB →

Qwen3.5 0.8B on other hardware

DeviceTotalTok/s est.
GeForce RTX 3060 Laptop
5.3 GB usable · 336 GB/s
1.2 GB 416 Runs great
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
1.2 GB 317 Runs great
M3 · 8 GB
5.4 GB usable · 100 GB/s
1.2 GB 114 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
1.2 GB 445 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
1.2 GB 137 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
1.2 GB 1247 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
1.2 GB 1188 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
1.2 GB 457 Runs great

All 114 devices, by tier →