LiquidAI/LFM3-1.7B-GGUF
AI model · https://huggingface.co/LiquidAI/LFM3-1.7B-GGUF
First seen by Oriel on .
AI summary
LiquidAI/LFM3-1.7B-GGUF packages LFM3-1.7B for local CPU and GPU inference through llama.cpp and compatible applications.
- Recommended general sampling uses temperature 0.1, top_k 50, and repeat penalty 1.1.
- Math and science workloads use temperature 1.0, top_p 0.95, and top_k 20.
- Llama.app, LM Studio, and Ollama provide supported interfaces, with specified minimum versions and platform availability.
- llama.cpp b11960 (v0.8.0) or newer can select quantizations using tags such as Q4_K_M.
- The Q4_0 repository build is a Quantization-Aware Distillation checkpoint trained to recover accuracy lost through Q4_0 quantization.
#gguf #llama.cpp #local inference #quantization
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Likes
Total likes reported by the source.
- Hugging Face Models: 231, latest observation ; +121 over observed period since
Downloads (30d)
Rolling 30-day downloads. A change in this value is not new downloads during the observed period.
- Hugging Face Models: 213,189, latest observation ; +195,024 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Models | LiquidAI/LFM3-1.7B-GGUF | https://huggingface.co/LiquidAI/LFM3-1.7B-GGUF Read discussion |