#qwen
37
2026-09-05
MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark
B
Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)
2026-11-08
kevinyvv/qwen-3-1.7b-finetune-proj
unrated
project on fine-tuning qwen to generate text w/o letter 'e'
2026-11-07
RustingStudio/RustingStrata
unrated
Pure-Rust MoE inference engine for Qwen3.5/3.6/3.8 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server. 2x llama.cpp prefill and decode on a 12 GB RTX 3060.
2026-11-04
simplexai-labs/PolyStrata
unrated
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
2026-10-26
lyramakesmusic/neuron-explorer
unrated
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
2026-10-21
jesdga95/basalt
unrated
Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell
2026-10-16
DominikBucko/qwen38-flash-next-2x3090
unrated
Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,865 tok/s; with 64 GB RAM 3,410 tok/s prefill · 84 tok/s decode. New: opt-in uncensored mode (runtime abliteration, no new weights).
2026-10-16
MiaAI-Lab/Qwen3.8-27B-16gb-NVIDIA-GPUs-one-click-install
unrated
Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux
2026-10-16
MiaAI-Lab/Qwen3.8-27B-DFlash2-EXL3-5.0bpw
unrated
Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards
2026-10-16
QwenLM/Qwen-Live-Harness
unrated
An open-source agent harness powered by the Qwen Omni Realtime API—see, hear, and act, with built-in memory.
2026-10-16
QwenLM/Qwen3.8-Flash-Next
unrated
Qwen3.8-Flash-Next is the foundation model developed by Qwen Team, Alibaba Group.
2026-10-16
QwenLM/RecreationWorld
unrated
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
2026-10-16
SnowSky1/universal-imagegen-agent
unrated
Bring the Codex imagegen workflow and prompt library to any agent; supports one-click npm/pnpm install, a companion skill, a standalone API, and a Qwen-Image-compatible gateway.
2026-10-16
Tongyi-MAI/Qwen-Planner-Agent
unrated
Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
2026-10-16
carloslfu/slotstream
unrated
Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients.
2026-10-16
denis-pplx/autojev
unrated
Full-weight Qwen decision model with calibrated probabilities, training code, REST API, and playground.
2026-10-16
iamyoki/qwen-image-2.1-skill
unrated
🎨 Agentic skill for Qwen-Image-2.1: Rewrites and optimizes text-to-image and multi-image editing prompts using official Alibaba specifications. Compatible with skills.sh and all AI agents.
2026-10-16
peonist-ai/halogen-server
unrated
The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)
2026-10-16
prabanta-dev/janas
unrated
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
2026-10-13
Show HN: Boole-1.7B, a 1-bit LLM that outperforms Bonsai-1.7B
unrated
Introducing Boole-1.7B, a 1-bit version of Qwen3-1.7B. Boole-1.7B retains 85.9% of BF16 performance using 247MB (13.9x smaller). It outperforms 1-bit Bonsai-1.7B and similar-sized LFM models, and nearly matches 1.58-bit Bonsai-1.7B. It’s intended for low-latency tasks using English and non-thinking mode. To learn more, - Blog: https://precisionnumerics.ai/blog/boole-1p7b - Weights: https://huggingface.co/precision-numerics/Boole-1.7B - Chat in browser: https://precisionnumerics.ai/chat/ We're going to ship more capable models soon for the open-source community. Let us know what models/capabilities you want to see next!
2026-09-26
eh4awrsalwdv/qwen3.8flash-qwen3.8-flash-api-ja
unrated
AI API relay/gateway Japanese guide · qwen3.8-flash / qwen3.8flash API: input $0.0914; cached_input $0.0114; explicit_cached_input $0.0114. Model IDs, parameters, curl and Python examples, OpenAI-compatible interface, top up from $1.
2026-09-26
oy8jfpo2qa8075/qwenimage3.0-qwen-image-3.0-api-cn
unrated
AI API relay/gateway Chinese documentation · qwen-image-3.0 / qwenimage3.0 API: default $0.0206; 1K $0.0206; 2K $0.0206. Model ID, parameters, curl and Python examples, OpenAI-compatible interface, top-up from $1.
2026-09-26
qh7wn6hrf9tx/qwenimage3.0-qwen-image-3.0-prompts
unrated
qwen-image-3.0 API (qwenimage3.0 / qwen image 3.0): default $0.0206; 1K $0.0206; 2K $0.0206. Model id, prompts settings, curl and Python examples over an OpenAI-compatible gateway,
2026-09-26
vc0ty0ori6s6/qwenimage3.0-qwen-image-3.0-api
unrated
qwen-image-3.0 API (qwenimage3.0 / qwen image 3.0): default $0.0206; 1K $0.0206; 2K $0.0206. Model id, api settings, curl and Python examples over an OpenAI-compatible gateway, $1
2026-09-26
y1m7ge9aeal27kut/qwen3.7flash-qwen3.7-flash-api
unrated
qwen3.7-flash API (qwen3.7flash / qwen3.7 flash): input $0.0229; cached_input $0.0046; explicit_cached_input $0.0023. Model id, llm settings, curl and Python examples over an OpenA
2026-09-22
Show HN: Using Qwen to track under-covered news
unrated
I'm helping launch this non-profit site which uses Qwen 3-32b to process thousands of news articles and analyze them by region, public interest, partisan lean, etc. This "Underreported in the US" section features stories covered abroad but have thin or absent coverage in US outlets. More on how we use LLMs below. Would love your feedback, good / bad / otherwise! https://pressaudit.org/AI-ethics
2026-09-13
Show HN: EarthToPixels – Turning real cities into explorable pixel art
unrated
Hi HN! A few friends and I built EarthToPixels, a project that turns real-world cities into explorable pixel-art maps. We fine-tuned an open-source Qwen image model and built a pipeline that takes aerial imagery, generates pixel-art tiles, and keeps neighboring generations visually continuous so they can be stitched into a large map. We built the pipeline to work with arbitrary coordinates rather than a specific city. For the first complete render, we chose our hometown: João Pessoa, Brazil. You can explore it here: https://earthtopixels.com/ Would love to hear what you think, especially about the technical side.
2026-09-11
Show HN: News observability site tracks coverage by party lean/distraction/etc.
unrated
Heya HN! I'm helping launch this site which uses Qwen 3-32b to process thousands of news articles and analyze them by region, public interest, partisan lean, etc. We would love your feedback!
2026-09-02
alphaparkinc/genpark-dynamic-aspect-ratio-visual-patch-tokenizer-skill
unrated
Dynamic aspect ratio visual patch tokenizer & 2D RoPE (Qwen2.5-VL style)