Hum Ma
hum-ma
AI & ML interests
None yet
Recent Activity
published a model 3 days ago
hum-ma/Qwen3.8-Flash-Next-UD-IQ1_Strata-GGUF updated a model 3 days ago
hum-ma/Qwen3.8-Flash-Next-UD-IQ1_Strata-GGUF liked a model 3 days ago
jakeatx/qwen3.8-27b-Swift1.5-Uncensored-ATX-AI2Organizations
None yet
plz make lightvae-lite-h3-decoder-int8-convrot.safetensors support comfyui
👍👀 2
1
#4 opened 28 days ago
by
xueqing12
Patch for scripts/check_applied.py
#107 opened about 2 months ago
by
hum-ma
Censorship
6
#4 opened about 2 months ago
by
PaleoBob
Request: Refusal-free (abliterated) weights for industrial, SIEM & agentic workflows
➕ 3
2
#8 opened about 2 months ago
by
amaxcz
How to set the time to (T=1)
👍 3
11
#1 opened 3 months ago
by
xueqing12
Comfyui support?
👍 1
4
#1 opened 2 months ago
by
bhasi
Stop wasting resources on models that are not optimized for consumer grade GPUs
🧠😔 6
10
#54 opened 3 months ago
by
adm1223
FP8 text encoder?
➕ 1
3
#8 opened 3 months ago
by
Linkram
Is there any plan to release a more lightweight model with fewer parameters?
➕ 2
4
#34 opened 3 months ago
by
makisekurisu-jp
how to use it as normal vae decode?
➕ 1
2
#10 opened 3 months ago
by
shivshankar
ComfyUI dual-clock Euler sampler for the Turbo LoRA (fixes 4-step audio noise)
🤗❤️ 7
6
#8 opened 3 months ago
by
condayeeees
Possibly a small mistake in docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md
#45 opened 3 months ago
by
hum-ma
"Alliterated / uncensored" TE's are snake oil.
4
#6 opened 3 months ago
by
Ada321
GGUF version?
👍 2
3
#2 opened 3 months ago
by
davoodkharmanzar
Will you provide pruned version for bf16?
➕ 7
3
#7 opened 3 months ago
by
John-Wong
Lora weights
2
#1 opened 8 months ago
by
EddyNeave
Function Calling on this model
🔥🚀 2
2
#1 opened over 1 year ago
by
mobinln
Regarding inference
#1 opened 9 months ago
by
hum-ma
Run times?
6
#51 opened 9 months ago
by
anonanonanon
Spaces or not, and is 0.6b enough?
😔 1
7
#45 opened 9 months ago
by
notafraud