LFM2.5 8B-A1B

At the default Q4_K_M, 105 of 140 phones have enough estimated usable memory; 105 also reach 3+ tokens/s. On Mac, 52 of 54 exact configurations pass using that quant or a smaller tracked fallback.

Params
8B (1B active)
Family
lfm
Released
2026-05
Tags
chat

Downloads & memory by quant

The download is only the weights — add KV cache and runtime to get what your phone actually needs. “Memory-fit” only means it can load; “usable” also requires an estimated 3+ tokens/s. Each row uses that row's quant. ★ = recommended.

QuantDownloadMemory neededPhone reality
Q4_04.8 GB~6.2 GB105 memory-fit · 105 usable
Q4_K_M5.2 GB~6.6 GB105 memory-fit · 105 usable
Q5_K_M6 GB~7.5 GB105 memory-fit · 105 usable
Q6_K7 GB~8.5 GB102 memory-fit · 102 usable
Q8_09 GB~10.6 GB59 memory-fit · 59 usable

LFM2.5 8B-A1B at Q4_K_M on 140 phones

This table is fixed to the recommended Q4_K_M, on each phone's largest RAM option. Counts for smaller quants above will differ. All phones are shown, sorted by fit and estimated experience; tap one for the full report.

PhoneChip · RAMNeedsSpeedVerdict

~ = bandwidth-based estimate · ✓ = measured on real hardware

LFM2.5 8B-A1B on 54 Mac configurations

Each Mac uses the recommended Q4_K_M at 4K context when it fits, or the largest smaller tracked quant that fits. Each row links to the full report with a macOS-specific setup guide.

MacUnified memoryQuantWorking budgetNeedsEstimated speedVerdict

FAQ

How much RAM do I need to run LFM2.5 8B-A1B on a phone?

At Q4_K_M, LFM2.5 8B-A1B needs ~6.6GB of usable memory (weights + KV cache + runtime). In practice that means a 12GB+ Android phone or a 12GB+ iPhone — iOS lets a single app use less of its RAM than Android does.

How fast does LFM2.5 8B-A1B run on a flagship phone?

On the Galaxy S25 Ultra (Snapdragon 8 Elite) it runs at ~53.2 tokens/s at Q4_K_M, estimated from memory bandwidth. Anything above ~8 tokens/s feels smooth for chat.

Can an iPhone run LFM2.5 8B-A1B?

Yes — the iPhone Air runs it at ~53.2 tokens/s at Q4_K_M, using 6.6GB of its ~7.8GB usable memory.

What is the best quantization of LFM2.5 8B-A1B for mobile?

Q4_K_M (5.2GB download) is the size/quality sweet spot of the 5 quants available. Total memory needed is ~6.6GB once the KV cache and runtime are counted — the download size alone understates it.

How many phones can run LFM2.5 8B-A1B?

105 of the 140 phones we track have enough estimated usable memory at Q4_K_M; 105 also reach our usable-speed threshold of 3 tokens/s, and 105 run smoothly. Memory-fit alone does not mean a good experience.

Which Macs can run LFM2.5 8B-A1B?

52 of the 54 exact Mac configurations we track have enough estimated working memory. Each Mac uses the recommended Q4_K_M when it fits, or the largest smaller tracked quant that fits, and separates installed unified memory, the macOS reserve, and estimated speed.

What is LFM2.5 8B-A1B good for on a phone?

It's tagged for chat. At 8B parameters (1B active — it's a MoE, so it decodes faster than its size suggests), it balances quality and speed for daily use.

Similar models

LFM2.5 2.6BLFM2.5-VL 3BTini Cybersec 8B-A1BLlama 3.1 8BMinistral 8B