Gemma 4 12B
Q4 GGUF download: unsloth/gemma-4-12b-it-GGUF - 7.12 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
14.2
AA Index
Coding
31.0
AA Index
Intelligence Index - Gemma 4 12B vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Coding Index comparison
Benchmark data from Artificial Analysis · updated 2026-10-19.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $0.10 |
| Output (per 1M tokens) | $0.30 |
| Median speed (hosted API) | 119 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-10-19. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| GPQA Diamond | 75.3 |
| HLE | 15.7 |
| IFBench | 73.5 |
| Terminal-Bench | 18.2 |
Source: Artificial Analysis component evals - updated 2026-10-19.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve google/gemma-4-12B-itNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Gemma 4 12B is a 12B-parameter apache-2.0 model from Google. It scores 14.2 on the Artificial Analysis Intelligence Index (coding 24.9). At Q4_K_M it needs roughly 7 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.
Benchmarks
Artificial Analysis Intelligence Index - Gemma 4 12B vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| Gemma 4 12B | 29 | 24.9 | 75.3 |
| Claude Opus 4.8 (max) | 61.4 | 56.7 | 92 |
| GPT-5.5 (xhigh) | 60.2 | 59.1 | 93.5 |
| Claude Opus 4.7 (max) | 57.3 | 52.5 | 91.4 |
| Gemini 3.1 Pro Preview | 57.2 | 55.5 | 94.1 |
| Qwen3.7 Max | 56.6 | 50.1 | 92.3 |
Source: Artificial Analysis (2026-06-08).
Popularity
Gemma 4 12B has 554,173 downloads in the last month on HuggingFace and 713 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Gemma 4 12B need?
Gemma 4 12B with 12B parameters needs approximately 7 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Gemma 4 12B better than other google models?
Gemma 4 12B has 12B parameters with 262,144 context - a strong choice for general use.
What license is Gemma 4 12B under?
Gemma 4 12B is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Gemma 4 12B well?
With 12B parameters, Gemma 4 12B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Gemma 4 12B?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~9 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Gemma 4 12B's context window handle?
Gemma 4 12B supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Gemma 4 12B?
Gemma 4 12B competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec