Sandesh Rajbhandari
sandeshrajx
AI & ML interests
None yet
Recent Activity
updated a model 9 days ago
sandeshrajx/openpangram-2b published a model 9 days ago
sandeshrajx/openpangram-2b new activity about 1 month ago
incoai/Qwen3.8-27B-DFlash2-GGUF:Code acceptance rate and token speed drops on write tool calls in pi coding agentOrganizations
Code acceptance rate and token speed drops on write tool calls in pi coding agent
👍➕ 3
6
#3 opened about 1 month ago
by sandeshrajx
Could you release the dataset used to train the lora so we may train it for smaller models i.e Gemma 4 / Qwen 3.5 4B?
👍 2
#3 opened about 2 months ago
by sandeshrajx
Ling 3.0 Flash Benchmarks Comparison in markdown
👍 4
#12 opened about 2 months ago
by sandeshrajx
Is this different from the official ComfyUI support for Minimax H3 int8 models?
1
#1 opened about 2 months ago
by sandeshrajx
request Qwen3.5-REAP-80B-A10B
🚀 1
5
#1 opened 7 months ago
by 
mwalol
Resource to create mxfp4 gguf models?
1
#2 opened 10 months ago
by sandeshrajx
Tool Calling doesn't seem to work.
1
#2 opened 10 months ago
by sandeshrajx
Illustrious and NoobAI versions please and Pony if possible.
🚀👍 15
14
#1 opened about 1 year ago
by 
krigeta
Tools calling fails even when I disable all tools and can't continue conversations.
3
#583 opened almost 2 years ago
by sandeshrajx
Apply for community grant: Personal project (gpu)
#1 opened over 2 years ago
by sandeshrajx
Librarian Bot: Add base_model information to model
#1 opened about 3 years ago
by 
librarian-bot