Gemma 4 31B

Google's largest Gemma 4 - dense 32.7B parameters (marketed as 31B) with a 256K context window under Apache 2.0.

Google · Gemma

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesHugging Face

Model checkpoints, context windows, provider support, local runtime compatibility, and license terms can change quickly. Verify the exact model card before production or commercial use.

Best for

Maximum Gemma quality for local chat, reasoning, and long-context work on 24 GB cards.

Who should use it

Maximum Gemma quality for local chat, reasoning, and long-context work on 24 GB cards.
Teams with access to hosted inference or server-class deployment paths.

Common workflows

Large open-weight chat, reasoning, and long-context workflows

Deployment and hardware notes

Ollama Q4_K_M is ~18 GB (26B A4B) / ~20 GB (31B): full-GPU on 24 GB cards, split placement with reduced throughput on smaller GPUs.

License and usage notes

Apache 2.0. Open weights. Verify the exact model card and license terms for the checkpoint or hosted provider you use.

Strengths

Open weights model option for Gemma workflows.
Maximum Gemma quality for local chat, reasoning, and long-context work on 24 GB cards.

Limitations

Q4 weights need a 24 GB card for full-GPU placement; below that Ollama splits across VRAM and system RAM. Verified against the HF config and Ollama library 2026-08-01.
Ollama Q4_K_M is ~18 GB (26B A4B) / ~20 GB (31B): full-GPU on 24 GB cards, split placement with reduced throughput on smaller GPUs.
Context window and limits: 256K tokens (max_position_embeddings 262144).
Verify the exact model card, provider docs, license, and serving support before production use.

Will Gemma 4 31B run on your machine?

Gemma 4 31B is 31B parameters and needs 21.5 GB of VRAM at Q4_K_M — 20 GB of weights plus 1.5 GB of runtime overhead for the inference server itself.

VRAM by quantization

Quantization	Weights	Needs (with overhead)	Quality
Q4_K_M	20 GB	21.5 GB	good

Fit on common hardware at Q4_K_M

Hardware	Memory the model can use	System RAM	Verdict
CPU Only	None (CPU only)	16 GB	Too large
RTX 4060 Laptop	8 GB	16 GB	Too large
RTX 3060 (12GB)	12 GB	32 GB	CPU offload
RTX 4060 Ti (16GB)	16 GB	32 GB	CPU offload
RTX 3090	24 GB	64 GB	Comfortable
Apple Silicon (Unified Memory) 36 GB	27 GB of 36 GB	36 GB	Comfortable
RTX 5090	32 GB	64 GB	Comfortable

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.

Apple Silicon shares one pool of memory between the system and the GPU, so a model cannot use all of it. These rows apply the same 75% usable fraction the Compatibility Checker uses, which is why a 36 GB Mac is graded on less than 36 GB.

Check Gemma 4 31B against your exact hardware How these verdicts are calculated