Robert Smith PRO
tcclaviger
AI & ML interests
Local SWE supporting LLMs that can be used for private data. Currently expanding capabilities to enable use of larger models supported by a custom tool set environment providing context 7 like knowledge with added DSA, Software design, and web crawling capabilities to enable autonomous expansion of knowledge as the LLM deems necessary.
Recent Activity
updated a model about 15 hours ago
tcclaviger/Tess-FP8 published a model about 15 hours ago
tcclaviger/Tess-FP8 updated a model about 15 hours ago
tcclaviger/Tess-27B-RFAOrganizations
None yet
Recommended temperature and other settings?
3
#8 opened 2 days ago
by 
cosmicnag
Complements To Your Work
2
#7 opened 3 days ago
by tcclaviger
How to turn off thinking....
👍 1
9
#14 opened about 1 month ago
by tcclaviger
Thanks for Quant and Docker Build!
51
#1 opened about 1 month ago
by 
djdeniro
Did you upload the wrong weights or are you faking a model?
3
#5 opened 20 days ago
by tcclaviger
For those curious
#1 opened 20 days ago
by tcclaviger
Any chances of vLLM support?
3
#3 opened 26 days ago
by 
SyferO
Supers Found in model
❤️ 2
9
#11 opened about 1 month ago
by tcclaviger
How to make thinking stop, so you can use none, low, mid, high thinking
#1 opened about 1 month ago
by tcclaviger
New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking about 1 month ago
Is this model reliable for serious work?
4
#7 opened about 1 month ago
by 
Nunodonato
New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking about 2 months ago
MTP should be left in place, its trivial to add back in and it is beneficial.
👍👀 3
12
#4 opened 2 months ago
by tcclaviger
New activity in DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF about 2 months ago
Qwen3.6-27B Local Deployment: llama-server Parameter Tuning Consultation
3
#8 opened 2 months ago
by 
jason888888
Bravo
❤️ 3
2
#1 opened 2 months ago
by tcclaviger
MTP Grafted back in, findings...
4
#6 opened 3 months ago
by tcclaviger
Is MTP possible?
3
#2 opened 3 months ago
by 
JDWarner
About this FP8
1
#1 opened 3 months ago
by 
sudo-0x2a
Model loading reduction from 5.5 minutes to 5.26 seconds
1
#19 opened 4 months ago
by tcclaviger
40B to 80B dense LLM: A better/smarter model than 122B that can still fit
1
#16 opened 4 months ago
by 
rtzurtz
Love the quant! Nicely done.
❤️ 1
3
#2 opened 4 months ago
by tcclaviger
MTP Working on AMD 4xR9700 and MXFP4 Custom Kernel
👍 1
1
#18 opened 4 months ago
by tcclaviger