Robert Smith's picture

Robert Smith PRO

tcclaviger

·

Rob-P-Smith

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 9 hours ago

tcclaviger/Step-3.7-Flash-240REAP-MXFP416

updated a model about 9 hours ago

tcclaviger/Qwen3.6-35B-A3B-MXFP416-MTP

updated a model about 9 hours ago

tcclaviger/Qwen3.6-27B-MXFP416-MTP

View all activity

Organizations

None yet

New activity in tcclaviger/Step-3.7-Flash-240REAP-MXFP416 1 day ago

Thanks for Quant and Docker Build!

#1 opened 4 days ago by

New activity in stepfun-ai/Step-3.7-Flash 5 days ago

Supers Found in model

#11 opened 7 days ago by

How to turn off thinking....

#14 opened 6 days ago by

New activity in tcclaviger/Step-3.7-Flash-240REAP 6 days ago

How to make thinking stop, so you can use none, low, mid, high thinking

#1 opened 6 days ago by

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking 6 days ago

Is this model reliable for serious work?

#7 opened 6 days ago by

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking 12 days ago

MTP should be left in place, its trivial to add back in and it is beneficial.

#4 opened about 1 month ago by

New activity in DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF 25 days ago

Qwen3.6-27B Local Deployment: llama-server Parameter Tuning Consultation

#8 opened 28 days ago by

New activity in Nimbz/Gemma-4-Gembrain-31B 27 days ago

Bravo

#1 opened 27 days ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 about 1 month ago

MTP Grafted back in, findings...

#6 opened about 1 month ago by

Is MTP possible?

#2 opened about 1 month ago by

New activity in Qwen/Qwen3.6-27B-FP8 about 2 months ago

About this FP8

#1 opened about 2 months ago by

New activity in Qwen/Qwen3.5-122B-A10B 2 months ago

Model loading reduction from 5.5 minutes to 5.26 seconds

#19 opened 2 months ago by

40B to 80B dense LLM: A better/smarter model than 122B that can still fit

#16 opened 3 months ago by

New activity in olka-fi/Qwen3.5-122B-A10B-MXFP4 2 months ago

Love the quant! Nicely done.

#2 opened 3 months ago by

New activity in Qwen/Qwen3.5-122B-A10B 3 months ago

MTP Working on AMD 4xR9700 and MXFP4 Custom Kernel

#18 opened 3 months ago by

New activity in MiniMaxAI/MiniMax-M2.1 5 months ago

mlx-community/MiniMax-M2.1-4bit templates issue

#12 opened 5 months ago by

New activity in mistralai/Devstral-2-123B-Instruct-2512 6 months ago

Official MXFP4 Quant please

#8 opened 6 months ago by

New activity in osmapi/MiniMax-M2-THRIFT 7 months ago

Will there be a paper or a blog on how you pruned the model while keeping its capabilities ?

#1 opened 7 months ago by

New activity in zai-org/GLM-4.5-Air 7 months ago

Add GPTQModel W4A16 INT format Quant ?

#13 opened 10 months ago by

New activity in tcclaviger/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-512k-ctx-W4A16 7 months ago

Currently in production on private service.

#1 opened 7 months ago by