quantization · 37 topics

ternary bonsai 2 27b gguf

nvidia qwen3 flash next nvfp4

why your local llm feels dumber than it is

unsloth qwen3.8 27b gguf

unsloth deepseek v4 flash 0731 gguf

prism ml ternary bonsai 27b gguf

turboquant kv cache quantization

prism ml bonsai 27b gguf

poolside laguna s 21 nvfp4

unsloth laguna s 2 1 gguf

deploying quantized models on amazon sagemaker ai with unsloth

gemma 4 qat models

advanced quantization algorithm for llms

lg exaone 3 5 awq

alibaba shrinks qwen3 32b to fit on a 24gb consumer gpu

moondream shrinks parakeet redux speech recognition to 178 mb

ornith 1 5 beats 35b models on reasoning

together ai fixes a hidden bias crashing llm reinforcement learning training

comfy org qwen image 2 1

prismml squeezes qwen3 8 27b

qwen3 8 27b gsq rco gguf

unsloth glm 5 3 flash gguf

quantization aware healing

liquid ai pipette on device benchmarking

liquid ai lfm2 5 on device phone benchmarks

empero qwen38 27b ridge gguf

liquidai lfm25 qad

qwen3 8 2 4t a95b fp8

angel slim hy3 gguf

unsloth deepseek v4 flash gguf

holo31 fast local computer use

hy mt 1 5 1 8b 1 25bit quantization

gated deltanet nvfp4 w4a4 minima

kv cache low rank adaptation

quantization triggered backdoors in language models

multilingual quantization tax

windowquant vlm kv cache quantization