No — not on this device
Gemma 3 12B at Q4_K_M needs 8.3 GB against 5.4 GB usable, and the shortfall of 2.9 GB is more than 256 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
Strong multilingual chat with images, sized for 12–16 GB cards. Gemma 4 12B is the same size and better.
Hardware requirements What hardware do I need to run Gemma 3 12B? →At Q4_K_M with an 8K context: a 12 GB GPU (RTX 3060 12 GB) 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 3 4B (3.3 GB) · Gemma 3 1B (1.2 GB)
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 22.7 GB | 24.1 GB | — | ~1.7 | Reference | 18.7 GB over |
| Q8_0 | 12.1 GB | 13.5 GB | — | ~3.1 | −0.1% ppl | 8.1 GB over |
| Q6_K | 9.3 GB | 10.7 GB | — | ~4.1 | −0.4% ppl | 5.3 GB over |
| Q5_K_M | 8.1 GB | 9.5 GB | — | ~4.7 | −0.8% ppl | 4.1 GB over |
| Q4_K_M | 6.9 GB | 8.3 GB | — | ~5.5 | −1.9% ppl | 2.9 GB over |
| Q3_K_M | 5.6 GB | 7.0 GB | — | ~6.8 | −5.4% ppl | 1.6 GB over |
| Q2_K | 4.8 GB | 6.2 GB | — | ~8.0 | −15% ppl | 0.8 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, 1 global in 6), which is why its cache barely grows with context.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/gemma-3-12b-it-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M1 · 8 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Gemma 3 27B 27.4B · same family |
Q4_K_M · 17.0 GB | — | Won't fit |
| Gemma 3 4B 4.3B · same family |
Q4_K_M · 3.3 GB | 16 | Runs great |
| Gemma 3 1B 1.0B · same family |
Q4_K_M · 1.2 GB | 68 | Runs great |
| Mistral NeMo 12B 12.2B · similar size |
Q4_K_M · 8.7 GB | — | Won't fit |
| Gemma 4 12B 12B · similar size |
Q4_K_M · 8.2 GB | — | Won't fit |
| Ministral 3 14B 13.9B · similar size |
Q4_K_M · 9.7 GB | — | Won't fit |
| Phi-4 14B 14.7B · similar size |
Q4_K_M · 10.4 GB | — | Won't fit |
Gemma 3 12B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
8.3 GB | ~14 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
8.3 GB | 32 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
8.3 GB | 9.8 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
8.3 GB | 89 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
8.3 GB | 85 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
8.3 GB | 33 | Runs great |