qwen · 48 topics

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

kev 0 5b

xiaomi mimo v2.6 distill qwen 9b

alibaba qwen3 8 livetranslate

alibaba qwen3 8 omni flash

prismml squeezes qwen3 8 27b

cerebras runs qwen 3 8 27b

davidau qwen38 27b turbo fable cold fusion

qwen3 8 27b gsq rco gguf

faunix qwen38 27b distillation 40k

alibaba qwen3.8 max 0902 tops code arena

qwen3 8 flash next fp8

huihui qwen3 8 27b abliterated

empero qwen38 27b ridge gguf

qwen38 27b uncensored mlx

huggingface state of open models qwen china

qwen 3 8 27b fp8

qwen qwen3 8 27b

alibaba opens qwen3 8 max weights

qwen3 8 2 4t a95b

alibaba releases qwen max open weight ai

qwen3 8 max

luffythefox qwen36 35b genesis

qwen3.6 27b fable fusion 711

rio llm merge controversy

hauhaucs qwen3 6 35b a3b uncensored

qwopus 3 6 27b v2 mtp gguf

qwen webworlddata dataset

internlm intern s2 preview 35b

qwen 3 7 dropped on qwen chat

cybersecqwen 4b

qwen3 6 27b dflash speculative decoding

unsloth qwen3 6 27b gguf

qwen3 6 27b uncensored hauhaucs aggressive

jwenv webgpu browser system one guide

kev decision models

unsloth qwen3 8 flash next gguf

jetbrains junie local

huihui ai qwen3 8 27b abliterated gguf

unsloth qwen3.8 27b gguf

building agentic workflows sagemaker bedrock

qwen agentworld 35b a3b

using local coding agents

qwen 3 0 6b fine tuning categorization

hn local model coding

2026 05 25 research qwen image edit 2511 loras fast

qwen3 7 max agent frontier

qwen agentworld