Can you run LFM2.5 2.6B locally?

LFM2.5 family · 2026 · 2.7B parameters (2.7B activated per token) · Hugging Face model card

How much VRAM does LFM2.5 2.6B need at each quantization?

LFM2.5 2.6B needs 1.8 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.

Hybrid conv/full-attention stack: config layer_types alternates 2 conv layers with 1 full_attention layer across 30 layers. No head_dim key is published in config.

Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (30 layers, 8 KV heads, head dim). Source: HF-verified 2026-09-30 via plain api (gated=false safetensors.total=2697198592 params=2.7B ctx=131072 license=other repo=LiquidAI/LFM2.5-2.6B@654f9463ce32b05d0429d76fe1f580b27d4c1ac0 layers=30 hidden=2048 kv_heads=8 heads=32 vocab=128000). MoE: num_experts=None num_experts_per_tok=None active_params_b=2.7 (dense; same as safetensors.total (config.json has no expert keys)). VRAM figures are documented calculations (Q4-class ~0.6 GB per B params, on active params for MoE rows), not measurements. release_date is the HF repo lastModified date observed on the verification pass. No tok/s or benchmark scores invented.

Which GPUs can run LFM2.5 2.6B locally?

At Q4_K_M with a 4k context, LFM2.5 2.6B needs 1.8 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.

Runs LFM2.5 2.6B comfortably (25%+ VRAM headroom)

Can a Mac run LFM2.5 2.6B?

Yes — these Apple Silicon machines fit LFM2.5 2.6B at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.

Can LFM2.5 2.6B run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for LFM2.5 2.6B at Q4_K_M. Their memory bandwidth is far below discrete GPUs, so expect a fraction of desktop generation speed.

Which pre-built systems can run LFM2.5 2.6B?

These mini PCs and workstations from our database fit LFM2.5 2.6B at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.

Frequently asked questions