#+HashtagPLUS#Hashtag the Web... #Tag your World!
Join

Menu

New post

#Qwen3

45 posts

Feed·
20 of 45 posts
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·about 17 hours ago
#5VEEyyUN
#devtocomputervision#technology#devto#dev#model

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
Exploring Open-Source Large Language Models for InkMind: Choosing a Better Poetry Continuation Model
📰
0Read More

Exploring Open-Source Large Language Models for InkMind: Choosing a Better Poetry Continuation Model

DEV Community: nlp·Yvette Kazeneza·4 days ago
#cn4xysrS
#devtonlp#devto#dev#model#pythia

Exploring Open-Source Large Language Models for InkMind: Choosing a Better Poetry...

15s
Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300
🖼️
0Read More

Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300

NVIDIA Technical Blog·Michelle Horton·8 days ago
#c1C0aMDn
#developer#model#nvidia#qwen3#attention

Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open ecosystem.

15s
Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding
🖼️
0Read More

Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding

NVIDIA Technical Blog·Michelle Horton·8 days ago
#YcKuzpif
#developer#nvidia#qwen3#model#flash

Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate.

15s
Qwen 3.8 Max now available on Vercel AI Gateway - Vercel
📰
0Read More

Qwen 3.8 Max now available on Vercel AI Gateway - Vercel

Vercel News·Walter Korman·9 days ago
#oqdu46uB
#vercel#gateway#model#qwen#alibaba

Call Alibaba's Qwen 3.8 Max through Vercel AI Gateway with one API key: no provider account, automatic fallbacks, spend tracking, and traces on every request.

15s
Qwen 3.8 Flash now available on AI Gateway - Vercel
📰
0Read More

Qwen 3.8 Flash now available on AI Gateway - Vercel

Vercel News·Zachary Chen·9 days ago
#ccURAByh
#vercel#flash#alibaba#qwen3#gateway

Call Alibaba's Qwen3.8-Flash through Vercel AI Gateway with one API key: no provider account, automatic fallbacks, spend tracking, and request traces.

15s
Qwen 3.8 Max 0902 now available on AI Gateway - Vercel
📰
0Read More

Qwen 3.8 Max 0902 now available on AI Gateway - Vercel

Vercel News·Zachary Chen·9 days ago
#0tGrBSFH
#vercel#alibaba#qwen3#gateway#coding

Call Alibaba's Qwen 3.8 Max 0902 through Vercel AI Gateway with one API key: no provider account, fallbacks, spend tracking, and traces on every request.

15s
Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
🖼️
802Read More

Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things

Hacker News·2 months ago
#DSU7ejnw
#simonwillison#qwen#qwen3#llm#reasoning

Friday’s big release was Qwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba’s Qwen research lab. I’ve been looking forward to this one: 27B is an …

15s