Alexey Satonin
Izenflamm
AI & ML interests
None yet
Recent Activity
new activity about 14 hours ago
DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored:Downloaded, quantized and ready for real work tests liked a model about 17 hours ago
DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored reacted to inflatebot's post with 🔥 5 days ago
i am BEGGING you people to stop shoving everything in the GGUF Hole and ship w4a8/w6a8 models for ComfyUI. Comfy has bespoke kernels for these! They're fast everywhere!
4 bits should be treated as the floor for DiT weights, if you really need 3 bits or lower you should just use a different model!
Also stop shilling nvfp4 you animals!!!Organizations
None yet
Downloaded, quantized and ready for real work tests
2
#4 opened about 15 hours ago
by Izenflamm
New activity in DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF 20 days ago
BF16 or MLX variants?
3
#22 opened 20 days ago
by Izenflamm
Trying it right now vs oQ4e
2
#2 opened 25 days ago
by Izenflamm
New activity in DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF 29 days ago
[pre-launch] older post, before refinements - 23 thinking modes? What?
👍 6
25
#3 opened about 1 month ago
by 
BebopVox
New activity in DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF 30 days ago
[pre-launch] benchmarks
14
#6 opened about 1 month ago
by 
Banaxi-Tech
New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF about 2 months ago
Hermes Agent ; Just amazing!!!
❤️ 1
1
#57 opened about 2 months ago
by Izenflamm
Some realworld testing
#6 opened 2 months ago
by Izenflamm
Great work. Bad advertisement.
👍 6
2
#17 opened 3 months ago
by Izenflamm
oQ4e quantization request
👍 1
2
#1 opened 3 months ago
by Izenflamm
New activity in DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking 4 months ago
Wonderful psychopath model! Love it!!!
1
#17 opened 4 months ago
by Izenflamm