Tomas Rolin

laserbeans's activity

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

New activity in logic65/Whittle-Qwen-3.8-35B-A3B about 14 hours ago

This is cool

2

#2 opened about 22 hours ago by

Miltos22

New activity in Venastine-Research/Xing4.0-29B-A4B-GGUF 5 days ago

Faster than Qwen3.6-35B-A3B ?

#4 opened 5 days ago by

laserbeans

New activity in Qwen/Qwen3.8-Flash-Next 6 days ago

How to limit thinking?

3

#71 opened 11 days ago by

MarbuelB

New activity in Cloudflare/clef-flash 6 days ago

"Flash" is usually MoE

🧠 2

#2 opened 6 days ago by

laserbeans

New activity in Cloudflare/clef 8 days ago

Demo for this model on Spaces

👍🔥 7

4

#1 opened 11 days ago by

multimodalart

New activity in deepseek-ai/DeepSeek-V4.1-Flash 25 days ago

Formal verification of Engram/Conditional Memory — safety review request

#59 opened 25 days ago by

laserbeans

New activity in Qwen/Qwen3.8-Flash-Next 25 days ago

Identified serious issue with Flash-Next hallucinating user instructions!

1

#57 opened 25 days ago by

laserbeans

New activity in mradermacher/qwen3.8-flash-coder-85gb-bf16-GGUF 30 days ago

Looping issue with Q4_K_M

1

#1 opened 30 days ago by

laserbeans

New activity in Jab1718/qwen3.8-flash-coder-26gb-gguf 30 days ago

51B engrams included?

#2 opened 30 days ago by

laserbeans

New activity in IFM/K2-Horizon-MoVA-36B-A4B about 1 month ago

12 tok/s @ 8GB VRAM for K2-Horizon IQ3_S GGUF vs. 30 tok/s for Nail 35B A3B

4

#7 opened about 1 month ago by

laserbeans

New activity in turboderp/Qwen3.8-Flash-Next-exl3 about 1 month ago

"All GPUs must be ampere (30 series) or newer."

1

#8 opened about 1 month ago by

laserbeans

New activity in mistralai/Leanstral-1.5-119B-A6B 3 months ago

TerminalBench optimization / Vibe integration / tool guards needed

🤯 2

#4 opened 3 months ago by

laserbeans

New activity in Qwen/Qwen-AgentWorld-35B-A3B 4 months ago

"no MTP"

👍 3

3

#3 opened 4 months ago by

laserbeans