DEV Community

#qwen

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Qwen 3.8 4-bit Benchmark RTX 4090: 1-bit is a Trap

Qwen 3.8 4-bit Benchmark RTX 4090: 1-bit is a Trap

Comments
7 min read
Same Prompt, Different Model: How I Benchmark AI Image Generators Without Fooling Myself

Same Prompt, Different Model: How I Benchmark AI Image Generators Without Fooling Myself

Comments
8 min read
Why China Is Doing So Good in AI... And Why Open Models Like Qwen and Kimi Might Matter More Than We Think

Why China Is Doing So Good in AI... And Why Open Models Like Qwen and Kimi Might Matter More Than We Think

1
Comments
10 min read
Qwen2.5 7B vs Qwen3 4B & 8B for Writing Correction: 60 Local Ollama Responses on Windows

Qwen2.5 7B vs Qwen3 4B & 8B for Writing Correction: 60 Local Ollama Responses on Windows

Comments
7 min read
Qwen3.8-Flash-Next Intelligence, Performance and Price Analysis!

Qwen3.8-Flash-Next Intelligence, Performance and Price Analysis!

Comments
5 min read
Qwen3 Embedding on Cloud TPU: Production Long-Context Retrieval with vLLM

Qwen3 Embedding on Cloud TPU: Production Long-Context Retrieval with vLLM

Comments
4 min read
A 27B AI model running in your office — no cloud, no monthly API bill

A 27B AI model running in your office — no cloud, no monthly API bill

Comments
3 min read
Deploying Qwen3.8-2.4T-A95B with vLLM: Verified GPU Pods, Quants, and Serving Recipes

Deploying Qwen3.8-2.4T-A95B with vLLM: Verified GPU Pods, Quants, and Serving Recipes

5
Comments
7 min read
Qwen3.8-2.4T Is Here: Alibaba 2.4 Trillion Parameter MoE Model Just Changed the Open Source AI Landscape

Qwen3.8-2.4T Is Here: Alibaba 2.4 Trillion Parameter MoE Model Just Changed the Open Source AI Landscape

1
Comments 1
3 min read
Qwen3 235B Tops the Agentic Benchmark - What That Test Actually Measures

Qwen3 235B Tops the Agentic Benchmark - What That Test Actually Measures

Comments
2 min read
Tested Qwen3-TTS 1.7B locally: it speaks German. It cannot read a part number.

Tested Qwen3-TTS 1.7B locally: it speaks German. It cannot read a part number.

1
Comments
8 min read
AI Dev Weekly #23: Qwen4 Architecture Preview, GPT-5.6 Lands in Kiro, Gemini Takes On Whisper

AI Dev Weekly #23: Qwen4 Architecture Preview, GPT-5.6 Lands in Kiro, Gemini Takes On Whisper

34
Comments 1
6 min read
Building a 13-Agent Marketing Society on Qwen Cloud — What Actually Broke, and What I Learned Fixing It

Building a 13-Agent Marketing Society on Qwen Cloud — What Actually Broke, and What I Learned Fixing It

1
Comments
3 min read
I built an AI agent that sells your stuff online and manages the listings

I built an AI agent that sells your stuff online and manages the listings

Comments
4 min read
I Built an Agent That Refuses to Act — Here's Why Qwen Made It Possible

I Built an Agent That Refuses to Act — Here's Why Qwen Made It Possible

Comments 1
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.