- 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
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.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K_L | 8.9 GBfile size | 9.5 GB8.9 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q2_K_LOllama ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q2_K_LDownload 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_0 | 12.6 GBfile size | 13.3 GB12.6 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_0Ollama ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_0Download 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_M | 13.5 GBfile size | 14.2 GB13.5 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_K_MOllama ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_K_MDownload 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_M | 15.9 GBfile size | 16.5 GB15.9 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q5_K_MOllama ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q5_K_MDownload 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_K | 18.3 GBfile size | 19.0 GB18.3 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q6_KOllama ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q6_KDownload hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-Q6_K.gguf" --local-dir LFM2.5-24B-A2B-GGUF |
| Q8_0 | 23.7 GBfile size | 24.4 GB23.7 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q8_0Ollama ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q8_0Download hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-Q8_0.gguf" --local-dir LFM2.5-24B-A2B-GGUF |
| BF16 | 44.7 GBfile size | 45.3 GB44.7 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:BF16Ollama ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:BF16Download hf download LiquidAI/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-BF16.gguf" --local-dir LFM2.5-24B-A2B-GGUF |
| F16 | 44.7 GBfile size | 45.3 GB44.7 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:F16Ollama ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:F16Download 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
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitLiquidAI/LFM2.5-24B-A2B-MLX-4bit | 12.6 GBfile size | 13.3 GB12.6 + 0.16 + 0.50 | Download page |
| MLX bf16LiquidAI/LFM2.5-24B-A2B-MLX-bf16 | 44.7 GBfile size | 45.3 GB44.7 + 0.16 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 44.7 GBfile size | 45.3 GB44.7 + 0.16 + 0.50 |
hf download LiquidAI/LFM2.5-24B-A2B --local-dir LFM2.5-24B-A2BOther conversions (17; sizes not read)
- LiquidAI/LFM2.5-24B-A2B-FP8 FP8, by the maker, 3.1k downloads
- LiquidAI/LFM2.5-24B-A2B-ONNX Other, by the maker, 524 downloads
- onnx-community/LFM2.5-24B-A2B-ONNX Other, 623 downloads
- cyankiwi/LFM2.5-24B-A2B-AWQ-INT4 AWQ, int4, 536 downloads
- aiprimebuilds/LFM2.5-24B-A2B-GPTQ GPTQ, 334 downloads
- infinity-ai-institute/LFM2.5-24B-A2B-NVFP4 NVFP4, 269 downloads
- primitive-ai/LFM2.5-24B-A2B-NVFP4A16 NVFP4, 215 downloads
- myroslavtryhubets/LFM2.5-24B-A2B-NVFP4A16 NVFP4, 170 downloads
- CoolJohn-AI/LFM2.5-24B-A2B-NVFP4-AutoRound NVFP4, 143 downloads
- FP8Enjoyer/LFM2.5-24B-A2B-MXFP4 Other, mxfp4, 137 downloads
- 0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-2.5 EXL3, 107 downloads
- 0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-3.5 EXL3, 100 downloads
- CanadaApollo6/LFM2.5-24B-A2B-M3TiS-3090 Other, 100 downloads
- 0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-4.0 EXL3, 98 downloads
- 0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-6.0 EXL3, 91 downloads
- urakozz/LFM2.5-24B-A2B-W4A16-g64 GPTQ, w4a16, 70 downloads
- Lottolabs/LFM2.5-24B-A2B-TT-Mixed-BFP4-BFP8-P150 GPTQ, 0 downloads
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
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.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| Liquidthe maker | $0.05 | $0.70 | 125k | fp8 | 162 | 0.4 s | 100.0% | yes | yes |
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
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- LiquidAI/LFM2.5-24B-A2B-DSpark2.5kUnreviewed
- summerAIO/diffusion-lfm2.5-24b-a2b24.0B2.2kUnreviewed
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.