Skip to content
localmodel.run

Text model · LFM

LF LFM2.5 8B-A1B: RAM and VRAM requirements

LFM2.5 8B-A1B needs about 6.3 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~4.8 GB to download; KV cache and overhead add the rest), or about 9.9 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 3060 Ti (8GB).

LFM family · 8.3B params (Mixture-of-Experts: activates only 1.5B of 8.3B params per token, so generation is faster than the total size suggests) · released May 2026.

Shopping for hardware? See what runs LFM2.5 8B-A1B →

Set up LFM2.5 8B-A1B on your hardware →

License LFM Open License v1.0 · Conditional ↓ 30.2K/mo ♥ 805 on HuggingFace
Q4_K_M GGUF
4.8 GB
Q8_0 GGUF
8.39 GB
Memory @ Q4 (4k)
~6.3 GB
Context
128 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

LFM2.5 8B-A1B runs on 41 of 49 tracked devices at Q4_K_M.

39 run well 2 tight fit 8 too small
Fit check Q4_K_M
Yes, it runs fast
needs 6.3 GB usable 10.5 GB
See the full breakdown
$ollama run lfm2.5:8b-a1b-q4_K_M

Memory breakdown

Weights (Q4_K_M)4.8 GB
+
KV cache (4k)0.7 GB
+
Overhead0.8 GB
=
Total6.3 GB

How context length changes it

4k context ~6.3 GB 32k context ~11.1 GB 128k context ~27.7 GB

Longer context grows the KV cache, which for LFM2.5 8B-A1B is sized by its 1.5B active params, not the full 8.3B. It needs ~6.3 GB at 4k and ~27.7 GB at 128k.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 3.5 GB est
Q3_K_M 4.1 GB est
Q4_K_M (default) 4.8 GB
Q5_K_M 5.9 GB est
Q6_K 6.8 GB est
Q8_0 8.39 GB
FP16 15.78 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run lfm2.5:8b-a1b-q4_K_M
llama.cpp
$ llama-cli -hf LiquidAI/LFM2.5-8B-A1B-GGUF:Q4_K_M
LM Studio
$ lms get LiquidAI/LFM2.5-8B-A1B-GGUF

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

NVIDIA GPUs

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down Qwen2.5-VL 7B 8.29B Next size up Qwen3-VL 8B 8.77B

Similar models

Head-to-head

FAQ

How much VRAM or RAM does LFM2.5 8B-A1B need?

At Q4_K_M, LFM2.5 8B-A1B needs about 6.3 GB (weights ~4.8 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~9.9 GB.

What is the Q4_K_M GGUF file size of LFM2.5 8B-A1B?

The Q4_K_M GGUF file is about 4.8 GB to download, and the Q8_0 GGUF is about 8.39 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~6.3 GB of memory at Q4_K_M.

Can LFM2.5 8B-A1B run on a laptop?

LFM2.5 8B-A1B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Is LFM2.5 8B-A1B cheaper to run because it is a MoE model?

It is faster, not lighter. LFM2.5 8B-A1B activates only 1.5B of 8.3B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 8.3B.

Can I use LFM2.5 8B-A1B commercially?

Conditionally. LFM Open License: free under $10M revenue; larger companies need a commercial license.

Understand the numbers

Short guides to the ideas behind LFM2.5 8B-A1B's memory and quant figures.

Liquid AI's reasoning-tuned MoE for on-device use: 8.3B total, 1.5B active, 128K context. Despite the A1B name the vendor card states 1.5B active params. Q4_K_M, Q8_0 and F16 sizes are measured vendor GGUF bytes converted to GiB (revision 49c14831707011e64d70b2ebd8462ba08d608434). The separately verified Ollama Q4_K_M model layer is 5,156,064,416 bytes.

Sources

Catalog updated 2026-11-01. Memory figures are estimates. See methodology.