No — not on this device

Gemma 4 12B at Q4_K_M needs 8.2 GB against 5.4 GB usable, and the shortfall of 2.8 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 · 6.7 GB Apache 2.0 Released 29 May 2026 Vision

The "unified" Gemma 4: text, image and audio in one 12B that fits a 12 GB card at Q4. 140+ languages.

Hardware requirements What hardware do I need to run Gemma 4 12B? →

At Q4_K_M with an 8K context: a 11 GB GPU (RTX 2080 Ti) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

Fits instead: Gemma 4 E4B (5.2 GB) · Gemma 4 E2B (3.5 GB)

The VRAM budget

weights 6.7 GB
Weights 6.7 GB KV cache @ 8K 0.81 GB Runtime overhead 0.6 GB Over budget 2.8 GB past 5.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 22.4 GB 23.8 GB — ~2.5 Reference 18.4 GB over
Q8_0 11.9 GB 13.3 GB — ~4.7 −0.1% ppl 7.9 GB over
Q6_K 9.2 GB 10.6 GB — ~6.1 −0.4% ppl 5.2 GB over
Q5_K_M 7.9 GB 9.3 GB — ~7.1 −0.8% ppl 3.9 GB over
Q4_K_M 6.7 GB 8.2 GB — ~8.3 −1.9% ppl 2.8 GB over
Q3_K_M 5.5 GB 6.9 GB — ~10 −5.4% ppl 1.5 GB over
Q2_K 4.7 GB 6.1 GB — ~12 −15% ppl 0.7 GB over

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (1024 tokens, 8 of 48 layers global), which is why its cache barely grows with context.

How to run it

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/gemma-4-12B-it-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 6.7 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.
Gemma 4 E4B
8.0B · same family
Q4_K_M · 5.2 GB 12 Tight fit
Gemma 4 26B-A4B
26.5B MoE · same family
Q4_K_M · 16.0 GB — Won't fit
Gemma 4 E2B
5.1B · same family
Q4_K_M · 3.5 GB 19 Runs great
Gemma 4 31B
31.3B · same family
Q4_K_M · 20.2 GB — Won't fit
Gemma 3 12B
12.2B · similar size
Q4_K_M · 8.3 GB — Won't fit
Mistral NeMo 12B
12.2B · similar size
Q4_K_M · 8.7 GB — Won't fit
Ministral 3 14B
13.9B · similar size
Q4_K_M · 9.7 GB — Won't fit

Every model against the M3 · 8 GB →

Gemma 4 12B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
8.2 GB ~15 CPU offload
GeForce RTX 2080 Ti
9.7 GB usable · 616 GB/s
8.2 GB 55 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
8.2 GB 32 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
8.2 GB 9.9 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
8.2 GB 90 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
8.2 GB 86 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
8.2 GB 33 Runs great

All 114 devices, by tier →