Skip to content
can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (96GB) run LFM2.5 8B-A1B (MoE)?

LFM · See model card · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: LFM2.5 8B-A1B (MoE) at FP16 · 17.0 GB weights · 88–132 tok/s on a Mac Studio M3 Ultra (96GB).

Arena Text Overall · style-controlled

UnratedNo exact match

No reviewed exact Arena match

No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. Local quantization quality is unmeasured.

Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh

Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986

Total memory at 4K context
17.8 GB
Weights + KV cache + runtime overhead
Estimated generation
88–132 tok/s
Estimated first token
~0.7s

Every quantization on this machine

On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.

LFM2.5 8B-A1B (MoE) quantizations on Mac Studio M3 Ultra (96GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q4_K_M5.2 GB6.0 GB132–198 tok/sRuns great
Q5_K_M6.0 GB6.9 GB127–191 tok/sRuns great
Q6_K7.0 GB7.8 GB123–184 tok/sRuns great
Q8_09.0 GB9.9 GB114–170 tok/sRuns great
FP1617.0 GB17.8 GB88–132 tok/sRuns great
Open the full calculator →Everything a Mac Studio M3 Ultra (96GB) runsLFM2.5 8B-A1B (MoE) on other machinesWhat to buy to run it →

Ran LFM2.5 8B-A1B (MoE) on a Mac Studio M3 Ultra (96GB)? Add your real numbers →