Skip to content

Can RTX 5090 run Shot Reader 8B?

Comfortable: GGUF Q8_0 needs 9.7 GB at 4K, batch 1; headroom 22.3 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 Q3_K_M4.9ComfortableVerified file
GGUF Q4_K_M5.9ComfortableVerified file
GGUF Q5_K_M6.7ComfortableVerified file
GGUF Q8_09.7ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K9.7Comfortable
16K11.6Comfortable
32K14.1Comfortable
128K28.9Tight

Generation speed

GGUF Q8_0: 126–167 tok/s · Derived range

Other model / GPU pairs