Pekka Finski
Deaquay
·
AI & ML interests
Lots
Recent Activity
updated a model about 15 hours ago
pekkAi/Qwen3.8-27B-Uncensored-NVFP4-RTX5090 published a model about 18 hours ago
pekkAi/Qwen3.8-27B-Uncensored-NVFP4-RTX5090 updated a model 7 days ago
pekkAi/Gemma-4-E2B-E4B-Abliterated-Text-Encoders-ComfyUIOrganizations
May I request to rebuild gemma-4-e2b, 07/16 version?
2
#1 opened 7 days ago
by
Perpetuity7
Have example workflow?
3
#2 opened about 2 months ago
by
4pr0000n
Work great with NVFP4 - can't wait for the R2V lora
4
#12 opened about 2 months ago
by
pat11
Issue with corrupted outputs (based on early broken version)
16
#1 opened 4 months ago
by
hugginging5454
Please share conversion script
12
#1 opened 4 months ago
by
Vigilence
Disabling thinking output in Comfy-ui in Qwen Nodes
4
#47 opened 6 months ago
by
Thrakks
Jinja Template
33
#1 opened 6 months ago
by
SerialKicked
Stuck on repating
👀 1
2
#1 opened 6 months ago
by
rarar89
[Request] Availability of Non-GGUF Weights for vLLM/SGLang Support
👀👍 7
5
#2 opened 7 months ago
by
Hyunwen
Update config.json
#1 opened 9 months ago
by
Deaquay
Your best model yet (even at 24k context)
🚀❤️ 4
3
#1 opened about 1 year ago
by
vevi33
Suggestion for 6GB VRAM
7
#3 opened about 1 year ago
by
skatiurrahaman
Best 72B Model so far... But for only 6K CTX
5
#1 opened over 1 year ago
by
Autumnlight
Very Horny, Settings Recommendations?
6
#2 opened about 2 years ago
by
UltimateTobi
Very Horny, Settings Recommendations?
6
#2 opened about 2 years ago
by
UltimateTobi
Very Horny, Settings Recommendations?
6
#2 opened about 2 years ago
by
UltimateTobi