- Size
- 354M parameterscounted 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
- 31 Mar 2026the date the repo was created
- Context length
- 125k tokensfrom the model's config
- Fine-tune
- of LiquidAI/LFM2.5-350M-BaseLfm2ForCausalLM
- On Hugging Face
- LiquidAI/LFM2.5-350M147k downloads in the last 30 days, 448 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: 0.09 GB, worked out from the model's config (LiquidAI/LFM2.5-350M), 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/LFM2.5-350M-GGUF (the maker's own conversion), 221k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q4_0 | 0.20 GBfile size | 0.80 GB0.20 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-350M-GGUF:Q4_0Ollama ollama run hf.co/LiquidAI/LFM2.5-350M-GGUF:Q4_0Download hf download LiquidAI/LFM2.5-350M-GGUF --include "LFM2.5-350M-QAD-Q4_0.gguf" --local-dir LFM2.5-350M-GGUF |
| Q4_K_M | 0.21 GBfile size | 0.81 GB0.21 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-350M-GGUF:Q4_K_MOllama ollama run hf.co/LiquidAI/LFM2.5-350M-GGUF:Q4_K_MDownload hf download LiquidAI/LFM2.5-350M-GGUF --include "LFM2.5-350M-Q4_K_M.gguf" --local-dir LFM2.5-350M-GGUF |
| Q5_K_M | 0.24 GBfile size | 0.84 GB0.24 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-350M-GGUF:Q5_K_MOllama ollama run hf.co/LiquidAI/LFM2.5-350M-GGUF:Q5_K_MDownload hf download LiquidAI/LFM2.5-350M-GGUF --include "LFM2.5-350M-Q5_K_M.gguf" --local-dir LFM2.5-350M-GGUF |
| Q6_K | 0.27 GBfile size | 0.87 GB0.27 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-350M-GGUF:Q6_KOllama ollama run hf.co/LiquidAI/LFM2.5-350M-GGUF:Q6_KDownload hf download LiquidAI/LFM2.5-350M-GGUF --include "LFM2.5-350M-Q6_K.gguf" --local-dir LFM2.5-350M-GGUF |
| Q8_0 | 0.35 GBfile size | 0.95 GB0.35 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-350M-GGUF:Q8_0Ollama ollama run hf.co/LiquidAI/LFM2.5-350M-GGUF:Q8_0Download hf download LiquidAI/LFM2.5-350M-GGUF --include "LFM2.5-350M-Q8_0.gguf" --local-dir LFM2.5-350M-GGUF |
| BF16 | 0.66 GBfile size | 1.3 GB0.66 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-350M-GGUF:BF16Ollama ollama run hf.co/LiquidAI/LFM2.5-350M-GGUF:BF16Download hf download LiquidAI/LFM2.5-350M-GGUF --include "LFM2.5-350M-BF16.gguf" --local-dir LFM2.5-350M-GGUF |
| F16 | 0.66 GBfile size | 1.3 GB0.66 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf LiquidAI/LFM2.5-350M-GGUF:F16Ollama ollama run hf.co/LiquidAI/LFM2.5-350M-GGUF:F16Download hf download LiquidAI/LFM2.5-350M-GGUF --include "LFM2.5-350M-F16.gguf" --local-dir LFM2.5-350M-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitLiquidAI/LFM2.5-350M-MLX-4bit | 0.21 GBfile size | 0.80 GB0.21 + 0.09 + 0.50 | Download page |
| MLX 8bitLiquidAI/LFM2.5-350M-MLX-8bit | 0.37 GBfile size | 0.97 GB0.37 + 0.09 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 0.66 GBfile size | 1.3 GB0.66 + 0.09 + 0.50 |
hf download LiquidAI/LFM2.5-350M --local-dir LFM2.5-350MOther conversions (5; sizes not read)
- LiquidAI/LFM2.5-350M-ONNX Other, by the maker, 1.4k downloads
- onnx-community/LFM2.5-350M-ONNX Other, 2.6k downloads
- litert-community/LFM2.5-350M Other, 965 downloads
- trymirai/LFM2.5-350M-L Other, 436 downloads
- liodon-ai/LFM2.5-350M-FP8 FP8, 13 downloads
The Hub tags 93 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
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-VL-450M449M43kUnreviewed
- Cactus-Compute/LFM2.5-350M21Unreviewed
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.