Skip to content

Can Radeon AI PRO R9700 32G run North Mini Code 1.0 30B-A3B?

Comfortable: GGUF Q4_K_M needs 20.0 GB at 4K, batch 1; headroom 12.0 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 Q3_K_M15.3ComfortableVerified file
GGUF Q4_K_M20.0ComfortableVerified file
GGUF Q8_034.3Does not fitVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K20.0Comfortable
16K20.4Comfortable
32K20.8Comfortable
128K23.5Comfortable

Generation speed

GGUF Q4_K_M: 365 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs