Pomni
Pomni
AI & ML interests
Pushing my GTX 1080 to its limits 🚀 I managed to get a 13B model with full GPU offload running once with relatively low quality loss.
Organizations
None yet
LiquidAI/LFM2.5-350M (smaller model so should be easier to test)
#633 opened 6 months ago
by Pomni
serious question
2
#2 opened 6 months ago
by 
cmoney1133
Adding `safetensors` variant of this model
1
#1 opened 7 months ago
by 
SFconvertbot
https://huggingface.co/Qwen/Qwen3.5-9B
1
#2019 opened 7 months ago
by Pomni
https://huggingface.co/MerlinSafety/Qwen3.5-4B-Safety-Thinking
1
#1999 opened 7 months ago
by Pomni
https://huggingface.co/tvall43/qwen3.5-18b-a3b-reap-coding-heretic-v0
1
#1994 opened 7 months ago
by Pomni
StableLM models
#589 opened 7 months ago
by Pomni
XML Question / Audacity OpenVINO integration
2
#1 opened 7 months ago
by 
animacio
Can someone please convert this to ggml for use with whisper.cpp
2
#1 opened over 1 year ago
by 
NedKelley1234
https://huggingface.co/MagicalAlchemist/Qwen3-1.7B-Magic_decensored
1
#1804 opened 8 months ago
by Pomni
GGML in 2025? Really?
1
#1 opened 11 months ago
by 
qpqpqpqpqpqp
Eval requests
#357 opened about 1 year ago
by Pomni
Eval request
1
#352 opened about 1 year ago
by Pomni
https://huggingface.co/EleutherAI/gpt-j-6b
10
#1157 opened about 1 year ago
by Pomni
Eval requests for Gemma 3n models
#327 opened about 1 year ago
by Pomni
https://huggingface.co/zelk12/MT5-Max-Merge_02012025163610-gemma-2-9B
1
#1152 opened about 1 year ago
by Pomni
https://huggingface.co/huihui-ai/Huihui-gemma-3n-E2B-it-abliterated
1
#1147 opened about 1 year ago
by Pomni
https://huggingface.co/K-intelligence/Midm-2.0-Base-Instruct
2
#1146 opened about 1 year ago
by Pomni
Eval request: sequelbox/Qwen3-14B-Esper3Grayline
#322 opened about 1 year ago
by Pomni
Eval request: SmolLM 135M Instruct
1
#320 opened about 1 year ago
by Pomni