🧩 Model Card: LiquidAI/LFM2-1.2B

• Type: Text-to-Text
• Think: No
• Tool Calling Support: No
• Prefix cache (server mode): Yes, saved prompts are reused (see Prefix Cache (Prompt Reuse))
• Base Model: LiquidAI/LFM2-1.2B
• Quantization: Q4_0
• Max Context Length: 32k tokens
• Default Context Length: 32k tokens (change default)
• Set Context Length at Launch

▶️ Run with FastFlowLM in PowerShell:

flm run lfm2:1.2b

🧩 Model Card: LiquidAI/LFM2-2.6B

• Type: Text-to-Text
• Think: No
• Tool Calling Support: No
• Prefix cache (server mode): Yes, saved prompts are reused (see Prefix Cache (Prompt Reuse))
• Base Model: LiquidAI/LFM2-2.6B
• Quantization: Q4_0
• Max Context Length: 32k tokens
• Default Context Length: 32k tokens (change default)
• Set Context Length at Launch

▶️ Run with FastFlowLM in PowerShell:

flm run lfm2:2.6b

🧩 Model Card: LiquidAI/LFM2-2.6B-Transcript

• Type: Text-to-Text
• Think: No
• Tool Calling Support: No
• Prefix cache (server mode): Yes, saved prompts are reused (see Prefix Cache (Prompt Reuse))
• Base Model: LiquidAI/LFM2-2.6B-Transcript
• Quantization: Q4_0
• Max Context Length: 32k tokens
• Default Context Length: 32k tokens (change default)
• Set Context Length at Launch

▶️ Run with FastFlowLM in PowerShell:

flm run lfm2-trans:2.6b

⚠️ This model is intended for single-turn conversations with a specific format, described here.

🧩 Model Card: LiquidAI/LFM2.5-1.2B-Instruct

• Type: Text-to-Text
• Think: No
• Tool Calling Support: No
• Prefix cache (server mode): Yes, saved prompts are reused (see Prefix Cache (Prompt Reuse))
• Base Model: LiquidAI/LFM2.5-1.2B-Instruct
• Quantization: Q4_0
• Max Context Length: 32k tokens
• Default Context Length: 32k tokens (change default)
• Set Context Length at Launch

▶️ Run with FastFlowLM in PowerShell:

flm run lfm2.5-it:1.2b

🧩 Model Card: LiquidAI/LFM2.5-1.2B-Thinking

• Type: Text-to-Text
• Think: Yes
• Tool Calling Support: No
• Prefix cache (server mode): Yes, saved prompts are reused (see Prefix Cache (Prompt Reuse))
• Base Model: LiquidAI/LFM2.5-1.2B-Thinking
• Quantization: Q4_0
• Max Context Length: 32k tokens
• Default Context Length: 32k tokens (change default)
• Set Context Length at Launch

▶️ Run with FastFlowLM in PowerShell:

flm run lfm2.5-tk:1.2b

🧩 Model Card: LiquidAI/LFM3-1.7B

• Type: Text-to-Text
• Think: Yes (on by default, toggleable)
• Tool Calling Support: Yes
• Base Model: LiquidAI/LFM3-1.7B
• Quantization: Q4_0 (the vendor’s quantization-aware-distilled build)
• Max Context Length: 32k tokens
• Default Context Length: 32k tokens (change default)
• Set Context Length at Launch
• FastFlowLM: 1.0.11 or later

▶️ Run with FastFlowLM in PowerShell:

flm run lfm3:1.7b

ℹ️ Released under the LFM Open License v1.0 (commercial use is limited by company revenue: check it before deploying).