Skip to content

Can Radeon RX 7900 XT run Ripple-65B-Preview?

Tight: GGUF IQ1_M needs 20.0 GB at 4K, batch 1; headroom 0.0 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 IQ1_M20.0TightVerified file
GGUF IQ2_XXS21.6Does not fitVerified file
GGUF IQ2_XS23.8Does not fitVerified file
GGUF IQ2_S27.2Does not fitVerified file
GGUF IQ3_XXS29.9Does not fitVerified file
GGUF IQ3_S34.5Does not fitVerified file
GGUF IQ4_XS41.1Does not fitVerified file
GGUF Q4_K_M41.2Does not fitVerified file
GGUF Q5_K_M50.8Does not fitVerified file
GGUF Q6_K60.9Does not fitVerified file
GGUF Q8_072.6Does not fitVerified file

Context capacity · GGUF IQ1_M

ContextTotal GBVerdict
4K20.0Tight
16K20.8Tight
32K21.9Does not fit
128K28.5Does not fit

Generation speed

GGUF IQ1_M: 46 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs