Menu

#Qwen3

64 posts

Feed·
20 of 64 posts
Tether AI Research ships BotPsy-0.8B, an open on-device agent model that leads its size class
🖼️
0Read More

Tether AI Research ships BotPsy-0.8B, an open on-device agent model that leads its size class

DEV Community: machinelearning·News·8 days ago
#p4Si5aeg

📅 November 11, 2026 • Tether AI Research Tether AI Research introduced BotPsy, a 0.8B-parameter...

15s
Deploying Underdog Bark 3.0 Pro: verbatim transcripts, custom backends and the chunk setting
📰
0Read More

Deploying Underdog Bark 3.0 Pro: verbatim transcripts, custom backends and the chunk setting

DEV Community: opensource·InferenceKey·14 days ago
#MoupwNgc
#devtoopensource#devto#dev#bark#qwen3

Bark 3.0 Pro got 6.28% of words wrong on 40 English clips, Qwen3-ASR-1.7B 7.03%. Where that gap comes from, and what to set before you deploy.

15s
Train a Modern VLM on One GPU: Qwen3-VL with Unsloth and Transformers 5.12.1
📰
0Read More

Train a Modern VLM on One GPU: Qwen3-VL with Unsloth and Transformers 5.12.1

DEV Community: computervision·Harpreet Sahota·14 days ago
#KTYiOvWp

A current vision-language fine-tuning guide that replaces an old Qwen2-VL notebook with a cleaner Qwen3-VL workflow, modern Transformers APIs, and a practical DocumentVQA example.

15s
Claude Code for Free in VS Code: No Login, No API Key (Ollama + Qwen 3.8)
📰
0Read More

Claude Code for Free in VS Code: No Login, No API Key (Ollama + Qwen 3.8)

DEV Community·TheCodeStreet·18 days ago
#M0DDrr7j
#dev#ollama#code#claude#model

Last time I ran Claude Code for free in the terminal. A lot of you asked the obvious follow-up: can I...

15s
How to Run Tencent WeVisOne-VL-4B Locally on 8 GB VRAM (Ollama Drops the Masks)
🖼️
0Read More

How to Run Tencent WeVisOne-VL-4B Locally on 8 GB VRAM (Ollama Drops the Masks)

DEV Community: computervision·Alan West·21 days ago
#5VEEyyUN

It refuses to box objects that aren't there 96.4% of the time vs 18.3% for Qwen3-VL-8B. Q4_K_M plus projector is ~3.2 GB; Ollama and llama.cpp commands inside.

15s