Why Gemma 4 31B (Dense) pressures system RAM
Gemma 4 31B (Dense) is a dense 31B network — every weight participates each token, so quantization choice dominates. Q4_K_M lands near ~17.4GB weights, plus ~0.08GB KV at 8K and ~6GB overhead (~23.5GB → 32GB kit). The 131K-token context ceiling is the sleeper cost: long-doc or agent traces inflate KV while the 31B slab stays fixed. Prefer dual-channel DDR5 bandwidth when CPU offload or mmap is involved.
What RAM kit to buy
A 32GB dual-channel kit is enough for quantized Gemma 4 31B (Dense) at modest context. Still prefer 2× matched SO-DIMM/UDIMM sticks; 1x RTX 3090 or RTX 4090 (24GB VRAM) covers the Flagship Consumer GPU GPU profile. If you chat with long pastes, jump a tier before the KV cache forces paging.
Workload notes
Gemma-class models like Gemma 4 31B (Dense) are dense-efficient on a single consumer GPU when quantized — system RAM still needs headroom for tokenizer, KV, and the host OS. At 31B, Gemma 4 31B (Dense) is a practical mid-size local model — sweet spot for single-GPU Q4/Q8 experimenters who still want headroom for IDE + Docker. Release window noted as April 2026; always re-check the official source before buying hardware for a specific checkpoint.