Best home rig for Gemma 4 31B

Will it fit my GPU? Best value GPU per euro →

Real, measured generation speeds for Gemma 4 31B on home hardware, fastest first. Different quants/engines aren't directly comparable.

Build	Quant	Engine	tok/s
RTX 5090: 2026 models (llamabench community)	llama-bench tg128 (quant per result)	llama.cpp	70.0	source
RTX 4090: 2026 models (llamabench community)	llama-bench tg128 (quant per result)	llama.cpp	43.8	source
HP ZBook Ultra G1a (Strix Halo laptop, 128 GB): Qwen3.6 35B-A3B at 59.4 tok/s, gpt-oss 120B at 44.7	4-bit	Ollama 0.34.0	8.8	source

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

Memory math: how much VRAM / RAM does Gemma 4 31B need?

Gemma 4 31B has 30.7B parameters (source: GGUF param count via llamabench.ai). Weight size = parameters × bits-per-weight ÷ 8, before context (KV cache) and runtime overhead.

Format	Bits/weight	Weights	Smallest common memory size that holds the weights alone
Q8_0	8.50	32.6 GB	48 GB
Q6_K	6.56	25.2 GB	32 GB
Q5_K_M	5.70	21.9 GB	24 GB
Q4_K_M	4.89	18.8 GB	24 GB
Q3_K_M	4.00	15.3 GB	16 GB
Q2_K	3.16	12.1 GB	16 GB

Bits-per-weight for GGUF quants are llama.cpp's own figures (llama.cpp quantize README). "As measured" rows apply the source's stated bits-per-weight to the parameter count; real files differ slightly because some layers stay at higher precision. Try other combinations in the VRAM calculator.

FAQ

How much VRAM does Gemma 4 31B need?

The weights are about 18.8 GB at Q4_K_M (30.7B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is RTX 4090 (24 GB) at 43.8 tok/s.

What is the fastest measured hardware for Gemma 4 31B?

RTX 5090: 70.0 tok/s generation (llama.cpp, llama-bench tg128 (quant per result)), from https://llamabench.ai/browse/rtx5090.

Which GPUs have measured results for Gemma 4 31B?

RTX 4090, RTX 5090, Strix Halo (Radeon 8060S).

Can it run on… RTX 4090 · RTX 5090 · Strix Halo (Radeon 8060S)