Skip to content

Can RTX 4070 run Xing4.0 29B-A4B?

Tight: GGUF IQ2_XXS needs 11.0 GB at 4K, batch 1; headroom 1.0 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 Q8_034.9Does not fitVerified file
GGUF Q6_K28.6Does not fitVerified file
GGUF Q5_K_M25.3Does not fitVerified file
GGUF Q4_K_M21.2Does not fitVerified file
GGUF IQ4_XS19.0Does not fitVerified file
GGUF Q3_K_M17.0Does not fitVerified file
GGUF IQ3_XXS15.3Does not fitVerified file
GGUF Q2_K13.6Does not fitVerified file
GGUF IQ2_XXS11.0TightVerified file

Context capacity · GGUF IQ2_XXS

ContextTotal GBVerdict
4K11.0Tight
16K11.5Tight
32K12.3Tight
128K17.0Does not fit

Generation speed

GGUF IQ2_XXS: 402 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs