Vladimir

vstiff's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 1 hour ago

Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design

Paper • 2610.23036 • Published 3 days ago • 4

Can Visual Generation Expand What Unified Multimodal Models Know?

Paper • 2610.21459 • Published 4 days ago • 9

upvoted a paper about 17 hours ago

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale

Paper • 2610.08430 • Published 13 days ago • 29

liked a model 3 days ago

unsloth/Qwen-Image-Layered-GGUF

Image-Text-to-Image • 20B • Updated 3 days ago • 81k • 70

reacted to yanghaojin's post with 🚀 3 days ago

view post

Post

2,986

Dear all,
we are happy to share that gbx v0.8.0, our local inference engine for Apple Silicon, runs the 105 GB Qwen3.8-Flash-Next on a 48 GB MacBook Pro by streaming MoE experts from the SSD. When the model fits in memory, it decodes up to 50% faster than omlx, Ollama and mlx-lm on the same Mac, with output identical token for token.
Full write-up: https://medium.com/@semamediadata/running-a-105-gb-qwen-on-a-48-gb-macbook-pro-f116fe493a49
Download gbx: https://github.com/GreenBitAI/gbx-lm/releases
Models: https://huggingface.co/collections/GreenBitAI/greenbitai-for-apple-silicon

See translation

• 
• 
• 
• 
• 

• 
• 
• 2 replies

·

🔥

8

8

🚀

2

2

👀

1

1

+

Reply

liked a model 3 days ago

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated Apr 24 • 601k • • 1.58k

liked 2 models 4 days ago

nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB

Image-Text-to-Text • 22B • Updated 4 days ago • 5.44k • 125

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

Image-Text-to-Text • 124B • Updated 2 days ago • 11.6k • 76

upvoted a paper 4 days ago

APEX: Asynchronous Prefix Denoising for Extreme Compression

Paper • 2610.12843 • Published 10 days ago • 53

liked a model 7 days ago

baidu/ERNIE-Image-Turbo

Text-to-Image • 8B • Updated Apr 17 • 3.23k • • 409

liked 2 models 12 days ago

autotrust/JEV-27B-VL

Image-Text-to-Text • 28B • Updated 5 days ago • 1.8M • 7.73k

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 13 days ago • 164k • • 2.67k

upvoted 2 papers 13 days ago

OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning

Paper • 2609.39490 • Published 19 days ago • 27

OSWorld-Pro: Process-based Evaluation for Computer Use Agents

Paper • 2609.24890 • Published 28 days ago • 28

liked a model 17 days ago

FINAL-Bench/POCKET-Darwin-180B-GGUF

Text Generation • 177B • Updated 4 days ago • 146k • 64

upvoted 5 papers 18 days ago

TabFM: A Zero-Shot Foundation Model for Tabular Data

Paper • 2609.37959 • Published 20 days ago • 21

TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models

Paper • 2609.37989 • Published 20 days ago • 12

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

Paper • 2609.38121 • Published 20 days ago • 27

Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model

Paper • 2609.40358 • Published 19 days ago • 22

PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

Paper • 2609.40285 • Published 19 days ago • 25