Skip to content
Weights Not Walls
Menu

LiquidAI

LFM2.5-24B-A2B

Reviewed
Size
24.0B parameters, 2.0B active (from the repo name)counted from the safetensors header on the Hub
Licence
custom, read it, LFM Open License v1.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
On the Hub since
12 Oct 2026the date the repo was created
Context length
128k tokensfrom the model's config
Fine-tune
of LiquidAI/LFM2.5-24B-A2B-BaseLfm2MoeForCausalLM
On Hugging Face
LiquidAI/LFM2.5-24B-A2B29k downloads in the last 30 days, 623 likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.16 GB, worked out from the model's config (LiquidAI/LFM2.5-24B-A2B), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

LiquidAI/LFM2.5-24B-A2B-GGUF (the maker's own conversion), 165k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q2_K_L8.9 GBfile size9.5 GB8.9 + 0.16 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q2_K_L
Ollama
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q2_K_L
Download
hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-QAD-Q2_K_L.gguf" --local-dir LFM2.5-24B-A2B-GGUF
Q4_012.6 GBfile size13.3 GB12.6 + 0.16 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_0
Ollama
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_0
Download
hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-Q4_0.gguf" --local-dir LFM2.5-24B-A2B-GGUF
Q4_K_M13.5 GBfile size14.2 GB13.5 + 0.16 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_K_M
Ollama
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_K_M
Download
hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-Q4_K_M.gguf" --local-dir LFM2.5-24B-A2B-GGUF
Q5_K_M15.9 GBfile size16.5 GB15.9 + 0.16 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q5_K_M
Ollama
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q5_K_M
Download
hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-Q5_K_M.gguf" --local-dir LFM2.5-24B-A2B-GGUF
Q6_K18.3 GBfile size19.0 GB18.3 + 0.16 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q6_K
Ollama
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q6_K
Download
hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-Q6_K.gguf" --local-dir LFM2.5-24B-A2B-GGUF
Q8_023.7 GBfile size24.4 GB23.7 + 0.16 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q8_0
Ollama
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q8_0
Download
hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-Q8_0.gguf" --local-dir LFM2.5-24B-A2B-GGUF
BF1644.7 GBfile size45.3 GB44.7 + 0.16 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:BF16
Ollama
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:BF16
Download
hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-BF16.gguf" --local-dir LFM2.5-24B-A2B-GGUF
F1644.7 GBfile size45.3 GB44.7 + 0.16 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:F16
Ollama
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:F16
Download
hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-F16.gguf" --local-dir LFM2.5-24B-A2B-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitLiquidAI/LFM2.5-24B-A2B-MLX-4bit12.6 GBfile size13.3 GB12.6 + 0.16 + 0.50Download page
MLX bf16LiquidAI/LFM2.5-24B-A2B-MLX-bf1644.7 GBfile size45.3 GB44.7 + 0.16 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights44.7 GBfile size45.3 GB44.7 + 0.16 + 0.50
hf download LiquidAI/LFM2.5-24B-A2B --local-dir LFM2.5-24B-A2B
Other conversions (17; sizes not read)

The Hub tags 91 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

1 provider serves this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
Liquidthe maker$0.05$0.70125kfp81620.4 s100.0%yesyes

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "LiquidAI/LFM2.5-24B-A2B:liquid", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.