Can I run this LLM?
Can a NVIDIA A100 (80GB) run LFM2.5 24B A2B?
LFM · LFM Open License v1.0 (restricted) · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: LFM2.5 24B A2B at FP16 · 48.0 GB weights · 166–249 tok/s on a NVIDIA A100 (80GB).
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 matchNo 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
- 166–249 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.
| Quant | Weights | Total memory | Speed | Fit |
|---|---|---|---|---|
| Q2_K | 8.0 GB | 8.9 GB | 301–451 tok/s | Runs great |
| Q3_K_M | 11.0 GB | 11.8 GB | 284–426 tok/s | Runs great |
| Q4_K_M | 14.9 GB | 15.8 GB | 264–396 tok/s | Runs great |
| Q5_K_M | 17.9 GB | 18.8 GB | 250–375 tok/s | Runs great |
| Q6_K | 21.9 GB | 22.7 GB | 235–352 tok/s | Runs great |
| Q8_0 | 25.5 GB | 26.4 GB | 222–333 tok/s | Runs great |
| FP16 | 48.0 GB | 48.8 GB | 166–249 tok/s | Runs great |
Ran LFM2.5 24B A2B on a NVIDIA A100 (80GB)? Add your real numbers →