standardApache 2.012B paramsOpen weights

Gemma 4 12B

12B parameter open-weight model. Google's flagship 12B open-weight model with 256K context. Q4 fits in 8–10 GB VRAM; strong default for MacBooks with 16 GB unified memory where KV-cache growth at long context is manageable. Benchmark against Qwen3 14B on your prompts — Gemma 4 leads on certain reasoning tasks.

Google · Gemma 4

Model overview

Gemma 4 12B is Google's current flagship open-weight model at the 12B size, pairing a 256K context window with the permissive Apache 2.0 license (a step up from the Gemma Terms of Use that covered the Gemma 3 line). At Q4 it fits in 8-10 GB of VRAM, making it a strong default for 16 GB MacBooks and mid-range consumer GPUs, though KV cache growth at longer context lengths is worth watching. It's worth benchmarking directly against similarly sized Qwen3 checkpoints on your own prompts, since each family tends to lead on different reasoning tasks rather than one being universally stronger.

Check your GPU fitWhat is VRAM?What is quantization?Local LLM quickstart

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesHuggingFace model card (google/gemma-4-12b-it), official docs, OpenSourcesAI editorial review.

VRAM figures are empirical estimates. Actual usage varies by runtime, context length, and system configuration. Verify on your specific hardware before production use.

Will Gemma 4 12B run on your machine?

Gemma 4 12B is 12B parameters and needs 9.1 GB of VRAM at Q4_K_M — 7.6 GB of weights plus 1.5 GB of runtime overhead for the inference server itself.

VRAM by quantization

QuantizationWeightsNeeds (with overhead)Quality
Q4_K_M7.6 GB9.1 GBgood
Q8_012.8 GB14.3 GBhigh
FP1624 GB25.5 GBreference

Fit on common hardware at Q4_K_M

HardwareMemory the model can useSystem RAMVerdict
CPU OnlyNone (CPU only)16 GBCPU offload
RTX 4060 Laptop8 GB16 GBCPU offload
RTX 3060 (12GB)12 GB32 GBComfortable
RTX 4060 Ti (16GB)16 GB32 GBComfortable
RTX 309024 GB64 GBComfortable

Comfortable means VRAM clears the requirement by 2 GB or more. Tight means it covers the requirement with no margin. CPU offload means the model does not fit in VRAM but system RAM is at least 1.6× the weights, so it will run at reduced speed — expect roughly 1–5 tokens per second. Figures are weights plus a fixed runtime overhead and exclude KV-cache growth, which scales with context length.

Check Gemma 4 12B against your exact hardwareHow these verdicts are calculated

Need more hardware for Gemma 4 12B? Open the PC Builder for the 13B / 14B tier →

Related models

Gemma 3 12B12B parameter model — shared focus: chat, rag, summarisation.Gemma 4 12B (QAT)12B parameter model — shared focus: chat, coding, summarisation.DeepSeek-R1 Distill 14B14B parameter model — shared focus: reasoning, coding, agents.CodeGemma 7BCoding assistant experiments and developer workflow prototypes.

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →