Henry Kroll III

hellork

·

http://anch.org

AI & ML interests

The best models that work for my setup are any of Qwen/Qwen3.6-35B-A3B GGUF with APEX quants. Consumer-grade (8GB GPU) text generation, image manipulation recognition, 3D model generation, language preservation and translation, and business use cases.

Recent Activity

liked a model 8 days ago

yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF

new activity 16 days ago

IFM/K2-Horizon-MoVA-36B-A4B:12 tok/s @ 8GB VRAM for K2-Horizon IQ3_S GGUF vs. 30 tok/s for Nail 35B A3B

liked a model 4 months ago

sentence-transformers/all-MiniLM-L6-v2

View all activity

Organizations

New activity in IFM/K2-Horizon-MoVA-36B-A4B 16 days ago

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

#7 opened 18 days ago by

New activity in Jackrong/Qwopus3.5-9B-Coder-GGUF 4 months ago

Reasoning loop in llamacpp

#2 opened 4 months ago by

New activity in unsloth/Qwen3.6-35B-A3B-MTP-GGUF 4 months ago

5060Ti + Qwen3.6-35B-A3B-MXFP4_MOE

#20 opened 4 months ago by

Absolutely no any speed increase: what wrong with my settings?

#18 opened 4 months ago by

New activity in unsloth/Qwen3.6-27B-MTP-GGUF 4 months ago

the trade off is not good (new update)

#28 opened 4 months ago by

Official llama.cpp slower than the https://github.com/am17an/llama.cpp.git

#30 opened 4 months ago by

UD-Q4_K_XL produces 0% MTP draft acceptance — blk.64.attn_/ffn_ quantized below the threshold for MTP rejection sampling

#32 opened 4 months ago by

New activity in KevinJK51/Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop-GGUF 4 months ago

mmproj?

#1 opened 4 months ago by

New activity in unsloth/Qwen3.6-27B-MTP-GGUF 4 months ago

IQ3XXS giving garbage output

#33 opened 4 months ago by

Official llama.cpp now has '--spec-type draft-mtp'

#29 opened 4 months ago by

Low VRAM<=8GB best result (40t/s WITHOUT MTP)

#17 opened 4 months ago by

New activity in AtomicChat/gemma-4-E4B-it-assistant-GGUF 5 months ago

Not working

#1 opened 5 months ago by

New activity in calcuis/chatterbox-gguf over 1 year ago

Just wanted to say thanks Calcuis

#1 opened over 1 year ago by

New activity in ggml-org/gguf-my-repo over 1 year ago

Completely incoherent model when converted Gemma 2 to IQ3_M with Imatrix file

#107 opened about 2 years ago by

New activity in bartowski/internlm2_5-7b-chat-1m-GGUF about 2 years ago

prompt template?

#1 opened about 2 years ago by

New activity in stabilityai/stable-audio-open-1.0 over 2 years ago

Cannot access gated repo

#2 opened over 2 years ago by