Yes, just — 0.5 GB spare

Qwen3 14B at Q4_K_M fits your M1 · 16 GB entirely in unified memory at 8K context, at an estimated 4.6 tokens per second. Past 11K 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 · 8.3 GB Apache 2.0 Released Apr 2025

The largest Qwen3 that fits a 12 GB card at Q4 with room for context.

Hardware requirements What hardware do I need to run Qwen3 14B? →

At Q4_K_M with an 8K context: a 16 GB GPU (RTX 5080) or a 24 GB Mac (M4 Pro). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 8.3 GB
Weights 8.3 GB KV cache @ 8K 1.25 GB Runtime overhead 0.6 GB Free 0.5 GB of 10.7 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 27.6 GB 29.4 GB — ~1.4 Reference 18.7 GB over
Q8_0 14.6 GB 16.5 GB — ~2.6 −0.1% ppl 5.8 GB over
Q6_K 11.3 GB 13.2 GB — ~3.4 −0.4% ppl 2.5 GB over
Q5_K_M 9.8 GB 11.6 GB 2K ~3.9 −0.8% ppl 0.9 GB over
Q4_K_M 8.3 GB 10.2 GB 11K 4.6 −1.9% ppl Recommended
Q3_K_M 6.7 GB 8.6 GB 21K 5.6 −5.4% ppl Long context
Q2_K 5.8 GB 7.6 GB 27K 6.6 −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/Qwen3-14B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 8.3 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 10.7 GB of 16 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03Only 0.5 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 11K context.
See all models for this rig Compare with another model

Related models on an M1 · 16 GB

ModelTotalTok/s est.
Qwen3 8B
8.19B · same family
Q4_K_M · 6.3 GB 8.3 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
Qwen3 32B
32.8B · same family
Q4_K_M · 21.0 GB — Won't fit
DeepSeek-R1-Distill-Qwen 14B
14.8B · similar size
Q4_K_M · 10.4 GB 4.6 Tight fit
Qwen2.5-Coder 14B
14.8B · similar size
Q4_K_M · 10.4 GB 4.6 Tight fit
Phi-4 14B
14.7B · similar size
Q4_K_M · 10.4 GB 4.6 Tight fit

Every model against the M1 · 16 GB →

Qwen3 14B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
10.2 GB ~8.3 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
10.2 GB 26 Tight fit
GeForce RTX 5080
14.4 GB usable · 960 GB/s
10.2 GB 70 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
10.2 GB 8.1 Tight fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
10.2 GB 73 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
10.2 GB 70 Runs great
M4 Pro · 24 GB
18.0 GB usable · 273 GB/s
10.2 GB 18 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
10.2 GB 27 Runs great

All 114 devices, by tier →