Local AI Advisor

Can MacBook Pro M5 Max 48 GB run Recursive Flint (40B-A2.5B)?

48 GB unified · 614 GB/s memory bandwidth · Recursive Flint (40B-A2.5B) has 39.8B parameters (2.5B active per token).

Short answer

Yes, excellent for chat and comfortable or better for every workload we test.

Best quantization for chat: MXFP4 (20 GB of weights) on LM Studio. Generation: 160–270 tok/s, leaving about 18 GB free for your other apps.

How it rates for each workload

Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.

WorkloadVerdictQuantGenerationFirst replyContext
Chatwith Open WebUIExcellentMXFP4160–270 tok/sunder 1 s8KDetails
Coding questionswith ContinueExcellentMXFP4150–250 tok/sunder 1 s16KDetails
Coding in a repositorywith AiderComfortableMXFP4130–210 tok/s≈2 s32KDetails
Agentic codingwith OpenCodeComfortableMXFP4120–190 tok/s≈3 s32KDetails
Long documents (64K)with Open WebUIExcellentMXFP480–130 tok/s≈8 s64KDetails

Speeds are bandwidth-based estimates; no direct benchmark exists for this pair. “First reply” is the time to read the workload’s opening prompt. How we calculate

Different tool, context size or workload?

These pages use typical settings. The full check models your exact setup.