Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run LFM2.5 24B A2B?

Yes — LFM2.5 24B A2B runs at FP16 (48.0 GB) at about 154–231 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

How much memory does LFM2.5 24B A2B need?

LFM2.5 24B A2B needs about 8.9 GB at 4K context at its smallest quantization. A NVIDIA RTX Pro 6000 Blackwell (96GB) has 96.0 GB.

Yes — LFM2.5 24B A2B runs on a NVIDIA RTX Pro 6000 Blackwell (96GB) at FP16

Yes — it runs great.

Runs great

Best fit: LFM2.5 24B A2B at FP16 · 48.0 GB weights · 154–231 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Pack & allocation notes: Q2–Q6 labels use Unsloth's dynamic UD-Qn_K_XL packs. The FP16 label uses BF16 weights. Runtime allocation can differ for this hybrid model. The LFM Open License v1.0 has commercial restrictions.

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: 48.8 GB; Weights + KV cache + runtime overhead
Estimated generation: 154–231 tok/s
Estimated first token: ~0.2s

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 24B A2B quantizations on NVIDIA RTX Pro 6000 Blackwell (96GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	8.0 GB	8.9 GB	293–440 tok/s	Runs great
Q3_K_M	11.0 GB	11.8 GB	275–413 tok/s	Runs great
Q4_K_M	14.9 GB	15.8 GB	254–381 tok/s	Runs great
Q5_K_M	17.9 GB	18.8 GB	240–360 tok/s	Runs great
Q6_K	21.9 GB	22.7 GB	223–335 tok/s	Runs great
Q8_0	25.5 GB	26.4 GB	210–315 tok/s	Runs great
FP16	48.0 GB	48.8 GB	154–231 tok/s	Runs great

Open the full calculator →Everything a NVIDIA RTX Pro 6000 Blackwell (96GB) runs LFM2.5 24B A2B on other machines What to buy to run it →

Ran LFM2.5 24B A2B on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →