qwen
for multimodal ai engineers
Why this scored 0
every term, weightedIts fastest-moving item, measured against the pace of its own source
Whether that velocity is itself speeding up, as a per-hour rate
How many independent communities its own items come from
Decays to zero over 14 days, counted from when we first saw it
Subtracted once something is big and old — sized by its biggest item, aged from when we first saw it
Weights are hand-tuned, not learned — we're calibrating them against realized trends as history accumulates. On an entity's first sighting there's no previous reading to compare against, so acceleration starts from a neutral prior rather than a measurement, and velocity falls back to engagement over its whole lifetime until a second reading exists. Full methodology
Outlook
high confidence · estimate, not a guarantee7-day
~0
range 0–12
14-day
~0
range 0–14
30-day
~0
range 0–19
Signal history
7-day window (free)projected trajectory (estimate, not a guarantee)
The evidence
The live items this entity's score aggregates — every community independently talking about it right now. This is the corroboration, shown, not claimed.
- 134
Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
Qwen 3.8 27B is strong but over-generates, needing careful prompt engineering. · for LLM developers, AI researchers
lobstersSteady 3 · qwenai24d ago - 234
Distilling Kimi Into Qwen Doesn't Give You Kimi. It Gives You Qwen With Kimi's Handwriting
Model distillation studied · for ai researchers
devtoSteady 3 · qwenai31d ago - 332
Qwen3.8 Max now ranked as the best overall model by agentic index
Qwen3.8 tops agentic index · for ai researchers
hackernewsSteady 3 · qwenai35d ago - 429
Show HN: I made a Raspberry with Qwen my local car AI
Local car AI on a Raspberry Pi using Qwen enables offline experimentation for autonomous-driving prototypes. · for ml engineers, hardware hackers
hackernewsSteady 2 · qwenai16d ago - 528
Qwen 3.8 27B
New 27B Qwen model released for LLM research and deployment. · for llm researchers
hackernewsSteady 2 · qwenai27d ago - 628
Qwen 3.8 27B is excellent, but it defaults to overthinking things
Qwen 3.8 27B shows strong performance but tends to overthink, affecting response speed. · for LLM developers
hackernewsSteady 2 · qwenai25d ago - 717
Building an AI Agent That Knows When Not to Guess (Qwen + MCP)
Ai agent building · for ai devs
devtoSteady 2 · qwenai57d ago - 816
Qwen 3.8
Qwen version updated · for dev founders
hackernewsSteady 3 · qwenother54d ago - 914
Swiftlet — Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert
Runs large models on Apple devices · for ai devs, ios teams
githubSteady 3 · qwenai−16 saturated37d ago - 1013
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast (image-text-to-text)
Image-text-to-text model · for ai researchers
huggingfaceSteady 3 · qwenai−6 saturated56d ago - 1112
Qwen/Qwen3.8-2.4T-A95B-FP8 (text-generation)
Text generation model · for ai researchers
huggingfaceSteady 2 · qwenai−13 saturated29d ago - 1211
Qwen 3.8 Max Preview
Qwen 3.8 max preview · for game devs
hackernewsSteady 3 · qwenother53d ago - 1310
Teaching a Qwen agent to forget
Teaching qwen to forget · for ai devs
devtoSteady 2 · qwenai57d ago - 1410
We built an AI board of directors on Qwen. Then we asked it whether we should migrate to Qwen.
AI board of directors · for ai founders
devtoSteady 2 · qwenai53d ago - 1510
Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone
Run large models on low memory · for ai researchers
hackernewsSteady 2 · qwenai38d ago - 169
peculiar-ragdoll/Qwen-Sharp-Chat-Templates
Qwen-Sharp chat templates provide ready-made prompts for .NET AI applications. · for AI developers
huggingfaceSteady 2 · qwenai−15 saturated19d ago - 170
froggeric/Qwen-Fixed-Chat-Templates
New chat template tool · for ai devs, chat teams
huggingfaceSteadyai−19 saturated59d ago - 180
Qwen/Qwen3.8-27B (image-text-to-text)
Qwen 3.8 27B now supports image-to-text generation. · for multimodal ai engineers
huggingfaceSteadyai−25 saturated27d ago - 190
bottlecapai/ThinkingCap-Qwen3.6-27B (image-text-to-text)
New image-text model · for ai researchers, dev teams
huggingfaceSteadyai−17 saturated59d ago - 200
unsloth/Qwen3.6-27B-MTP-GGUF (image-text-to-text)
Image text model · for ai researchers
huggingfaceSteadyai−18 saturated59d ago