Apple publishes LensVLM-9B, a Qwen3.5-9B finetune, on Hugging Face

Apple has published LensVLM-9B on Hugging Face. Victor M describes it as a finetune of Qwen3.5-9B that turns long documents into small page images to save tokens, then retrieves the full text of only the pages relevant to a question.

#apple #lensvlm-9b #qwen #hugging-face

View original post ↗

Previous articleAnthropic says Claude found an unknown enzyme system in bacteriophage DNA Next articleCohere Model Vault is now available in Canada

Related AI news

Qwen highlights live Qwen-Image-2.1 demo on Hugging Face Spaces

Qwen highlighted a Hugging Apps live demo of Qwen-Image-2.1 on Hugging Face Spaces, saying one checkpoint covers generation and editing and can be tried in the browser with no setup. Hugging Apps described the model as a 7B-parameter native generation and editing model with up to 10 image references.

QQwen•9/20/2026, 19:58:48•

#qwen #qwen-image #hugging-face #image-generation #image-editing

Together AI publishes Tev1-4B-experimental weights on Hugging Face

The Tev1-4B-experimental weights are in the togethercomputer repository on Hugging Face. Together AI describes the model as an experiment meant to show how specialized decision models can be trained fairly easily.

TTogether AI•1d 20h 21m ago•

#together-ai #tev1-4b #hugging-face #model-weights

Together AI releases tev1-4B-experimental on Together serverless

The Jev-like classifier is finetuned on Qwen3.5 4B and priced at $0.042/M input and $0/M output. Together AI is also releasing a data recipe and a finetuning tutorial, and says training Tev1 cost $17.

TTogether AI•1d 20h 26m ago•

#together-ai #tev1 #qwen #model-release #pricing

Qwen3.8 Max Prime is live on OpenRouter

OpenRouter now hosts Qwen3.8 Max Prime from Alibaba_Qwen, describing it as a higher-throughput variant of Qwen3.8 Max with the same 2.4T-parameter capabilities.

OOpenRouter•1d 20h 56m ago•

#openrouter #qwen #qwen3.8-max-prime #model-availability

NVIDIA's Skill2Env compiles public Agent Skills into 7,971 terminal tasks

A Codex planner and creator turn each skill into tested terminal workflows, using a rubric taken from that skill's own quality criteria. Outcome-only RL moved Qwen3.8-27B from 49.4% to 54.1% on Terminal-Bench 2.1, while adding the rubric reached 50.1% but won more trajectory comparisons.

DDAIR.AI•1d 21h 53m ago•

#skill2env #nvidia #agent-skills #reinforcement-learning #qwen

Reset history AI News FAQ Email alerts RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.