Skip to content

Can A40 48G run Apex 35B V1.0?

Comfortable: GGUF Q8_0 needs 39.6 GB at 4K, batch 1; headroom 8.4 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_M18.7ComfortableVerified file
GGUF Q4_K_M23.9ComfortableVerified file
GGUF Q5_K_M28.8ComfortableVerified file
GGUF Q8_039.6ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K39.6Comfortable
16K39.9Comfortable
32K40.2Comfortable
128K42.3Tight

Generation speed

GGUF Q8_0: 229 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs