Best Gemma 4 12B quant for a 12GB GPU

Short answer: Q6_K from unsloth. Of the 5 Gemma 4 12B files we tested that fit fully in 12GB with a 8192-token context, it has the highest measured accuracy (88.2% on GSM8K + MMLU + ARC-C, 95% CI 85.1–90.7). KLD pending: ranked by accuracy for now.

Smallest diff that fits 12GB

Q6_K by unsloth

File size: 9.11 GB
KLD: pending
Accuracy (500 items): 88.2% (85.1–90.7)
Tool calls: 86.0%
Accuracy: tied with best
Generation: 57 t/s full GPU

gemma-4-12b-it-Q6_K.gguf

Runner-up

Q4_K_M by unsloth

File size: 6.63 GB
KLD: pending
Accuracy (500 items): 87.4% (84.2–90.0)
Tool calls: 85.5%
Accuracy: tied with best
Generation: 72 t/s full GPU

gemma-4-12b-it-Q4_K_M.gguf

Fastest that fits

UD-Q2_K_XL by unsloth

File size: 4.34 GB
KLD: pending
Accuracy (500 items): 67.2% (63.0–71.2)
Tool calls: 58.5%
Accuracy: ▼ below best on GSM8K, MMLU, ARC-C
Generation: 98 t/s full GPU

gemma-4-12b-it-UD-Q2_K_XL.gguf

Other budgets: 8GB 16GB 24GB · all 6 Gemma 4 12B quants

How we picked

We estimate VRAM need as file size + f16 KV cache for 8192 tokens + about 0.6GB of compute buffers, and keep 0.5GB free for your desktop. Among files that fit, we rank by mean KL divergence against the BF16 model's logits, then by tool-call score. If you need a longer context, step down one quant level or quantize the KV cache (-ctk q8_0 -ctv q8_0). Methodology.

GPU too small? Rent one.

Run a 32B model at Q6/Q8, or a 70B, on a cloud GPU for an hour or two instead of buying hardware.

RunPod

Cloud GPU pods with 24-80GB cards (RTX 4090 / 5090 / A100 / H100) for big quants or BF16 reference runs.

Rent on RunPod

Vast.ai

GPU marketplace for renting a 24-48GB card for an evening of testing.

Rent on Vast.ai

Your GPU cloud here

Sponsor slot. Sponsors never influence scores or rankings.

Sponsor QuantDiff

Referral links: QuantDiff may earn credit if you sign up. Referral partners have no say in scores or rankings.