Skip to content

Can A100 40G run Gemma 4 31B IT?

Comfortable: GGUF Q5_K_M needs 25.3 GB at 4K, batch 1; headroom 14.8 GB.

Text input, FP16 KV cache, one card. Unified-memory capacity uses the GPU guide’s usable limit; negative headroom may require host offload. Speed source settings may differ from this 4K estimate.

Measured runs

No measured run for this pair. Sizing is an estimate, not a runtime test.

Quant memory at 4K

QuantTotal GBVerdictWeight sizing
GGUF Q4_K_M22.1ComfortableVerified file
GGUF Q4_020.1ComfortableVerified file
GGUF Q8_035.7TightVerified file
GGUF Q3_K_M18.3ComfortableVerified file
GGUF Q5_K_M25.3ComfortableVerified file

Context capacity · GGUF Q5_K_M

ContextTotal GBVerdict
4K25.3Comfortable
16K26.3Comfortable
32K27.7Comfortable
128K35.9Tight

Generation speed

GGUF Q5_K_M: 72 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs