LFM2.5-24B-A2B
liquidai/lfm-2.5-24b-a2b- Liquidai
- Family · LFM2
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context125K
Max output8K
Input / 1M$0.05
Output / 1M$0.7014× input
Usage
Tokens / day680.3M▲ 42% 7d
Usage rank#216
Requests / day23.7K
Tool calls / req0.35
Per request · 30 days
Avg input9.5K0.6× median
Avg output1.4K2.0× median
Cache hit81%1.2× median
Reasoning share91%1.6× median
Tool-call failures10%5.4× median
Consumption
Peak 680.3M 1 NovLow 53.2M 24 OctRank today #216
News & trends
Trending · 14 days
News · latest from Liquidai
Benchmarks
Benchmark data: Artificial AnalysisOutput speed#10/334285 tok/s4.5× faster than median
First token#60.24 s4.4× quicker than median
Family progress
Intelligence Index
- Family releases8.4
Technical details
- Tokenizer
- Other
- License
- other
- Parameters
- 24B
- Moderation
- none
- Downloads · likes
- 31.1K · 596
Request parameters 18
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_k
- min_p
- max_tokens
+8 more
- max_completion_tokens
- stop
- seed
- frequency_penalty
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Fast private agents on local hardware
- Tool calling in lightweight agents
- Structured output extraction
- Self-hosted assistants with open weights
Think twice for
- Hardest reasoning tasks
- Image input
- Very long generated outputs
Same family
LFM2- 4.8
- 5.9
- 4.9
- 5.2
- 5.2
- 5.2
- 7.2
- 8.4
Want LFM2.5-24B-A2B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.