Spark-X2.6-4B
This repository is a conversion of XHToken/Spark-X2.6-4B to LiteRT-LM (.litertlm), made with litert-torch 0.9.3 for LiteRT-LM 0.19.0: on...
This repository is a conversion of XHToken/Spark-X2.6-4B to LiteRT-LM (.litertlm), made with litert-torch 0.9.3 for LiteRT-LM 0.19.0: on...
This repository is a community conversion of Qwen/Qwen3.8-27B to the LiteRT-LM (.litertlm) format, made with litert-torch (commit 115a1360...
A Q80 GGUF file of basal-omni-pico (0.8B, built on Qwen3.5-0.8B-Base) for llama.cpp, on the CPU or on a...
Original model: https://huggingface.co/LiquidAI/LFM2.5-24B-A2B Model details: — Parameter count: 24B (source checkpoint) — Input support: text — Speculative decoding:...
LiquidAI/LFM2-2.6B-Exp converted to the LiteRT-LM (.litertlm) format for Google’s LiteRT-LM runtime. Tested on litert-lm 0.18.0 on a Mac;...
This model LiquidAI/LFM2.5-24B-A2B-MLX-6bit was converted to MLX format from LiquidAI/LFM2.5-24B-A2B using mlx-lm version 0.32.0. Quantized to 6 bits...
Ritchie — это компактная 100,7-параметрическая языковая модель, созданная специально для программирования на Си, названная в честь Денниса Ритчи,...
A decensored variant of LiquidAI/LFM2.5-8B-A1B, produced with Heretic v1.4.0 (directional ablation / «abliteration»). Liquid’s hybrid conv+attention MoE keeps...
ZERO LOOP is a tiny foundation language model from Zero Labs, trained from scratch. At 19.9M parameters it...
Measured on device (edge-compat, spark-x2.5-1.7b-int4): Galaxy S26 · LiteRT-LM 0.16.0 · GPU · decode 17.8 tok/s · prefill...