LFM3-1.7b seems impressive
Summary
The author tested Liquid AI's LFM3-1.7B model (Q8_0 GGUF via llama.cpp/ROCm) for compression and summarization, reporting strong prefill/decode throughput on Strix Halo and tensor-split 7900 XTX+XT setups, plus unexpectedly coherent performance at 32k-64k context lengths for a 1.7B model.
Similar Articles
LiquidAI/LFM3-1.7B
Liquid AI released LFM3-1.7B, a 1.73B-parameter tri-hybrid text model designed for local agents and edge deployment with a 256K-token context window, fitting in about 1 GB of memory at 4-bit precision and supporting single-GPU fine-tuning for domain specialization.
LFM3-1.7B quantization report: 3.6 GB VRAM lossless; 2.2 GB with modest degradation
A quantization report for LiquidAI's LFM3-1.7B shows it runs losslessly in 3.6 GB VRAM (2.2 GB with modest degradation) and outperforms MiniCPM5-2B on LiquidAI benchmarks while offering 2x context in half the memory.
A 2.6B model with tool calling and 128K context now runs at 30 tok/s on a phone
Liquid AI released LFM2.5-2.6B, a 2.69B parameter model with 128K context and tool calling, optimized for multi-step agent workflows and capable of running at 30 tok/s on a phone with a 1.67GB Q4_K_M GGUF, though coding and knowledge-heavy tasks remain weak compared to larger models.
LFM2.5-2.6B model+KV cache quantization report
A detailed report on quantizing LiquidAI's LFM2.5-2.6B model with various GGUF and KV cache quantizations, showing it fits on an 8GB Raspberry Pi with minimal degradation, but warning against Q4_K_M.
LFM2.5-2.6B is out
Liquid AI released LFM2.5-2.6B, a new tiny model focused on agentic capabilities. The author is excited to test it for high-volume tasks like document summarization.