Skip to content

Can Mac M3 Max 48G run Clover-35B-A3B-Preview?

Comfortable: GGUF Q5_K_M needs 28.3 GB at 4K, batch 1; headroom 7.8 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 Q3_K_M18.2ComfortableVerified file
GGUF Q4_020.9ComfortableVerified file
GGUF Q4_K_M23.4ComfortableVerified file
GGUF Q5_K_M28.3ComfortableVerified file
GGUF Q8_038.6Does not fitVerified file

Context capacity · GGUF Q5_K_M

ContextTotal GBVerdict
4K28.3Comfortable
16K28.5Comfortable
32K28.9Comfortable
128K30.9Comfortable

Generation speed

GGUF Q5_K_M: 181 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs