Tim Becker
wsbagnsv1
AI & ML interests
Mostly interested in LLMs, particularly linear attention methods at the moment.
Username on discord is th3pun1sh3r for easy contact
Recent Activity
liked a model 9 days ago
zai-org/GLM-5.3-Flash liked a model 15 days ago
TelperionAI/Qwen3.8-27B-NVFP4-AWQ-GPTQ liked a model 21 days ago
Qwen/Qwen3.8-27BOrganizations
My deepest respect and admiration goes out to the Qwen team!!
👍❤️ 65
16
#1 opened 5 months ago
by 
testamentaddress01
why no Q8_K quant?
1
#10 opened 9 months ago
by 
MasterM007
Holocine: interesting new wan model, paper and weights published
1
#9 opened 10 months ago
by 
WernerrenreW
Config issue
2
#1 opened 11 months ago
by wsbagnsv1
The text encoder and VAE files are not in this repo, as it states.
1
#12 opened 11 months ago
by 
ljredux
no example workflow?
3
#1 opened 11 months ago
by 
HeyGoodEnough
Animate v2?
1
#9 opened 11 months ago
by 
pat11
Artifacts in output using lower quants (q2 and q4 tested)
👍 1
50
#6 opened 12 months ago
by 
Able2
Any chance of Qwen Image Edit quants?
🚀 1
5
#10 opened about 1 year ago
by 
willhsmit
Catostrophic Model Failure
👍 2
15
#7 opened 11 months ago
by 
kieraisverybored
wan22animate v2 gguf please
2
#8 opened 11 months ago
by 
nicehero
Сonversion script?
1
#7 opened 11 months ago
by 
hfmaster
Could you make a set of quants for the new 12B version?
👍 2
16
#1 opened 11 months ago
by 
HDiffusion
Quantization support
➕ 6
5
#5 opened about 1 year ago
by 
princemjp
Qwen-Image-Edit-2509-Q6_K.gguf: Bad images generated
1
#10 opened 11 months ago
by 
TripleDug
ComfyUI ?
9
#1 opened 11 months ago
by 
AI-Joe-git
Is it true llama.cpp always de-quantizes GGUF to FP16?
2
#13 opened 11 months ago
by 
Phaserblast
kSampler Error: No module named 'sageattention'
4
#6 opened 11 months ago
by 
tokenprovider
please create a guff from the e4m3fn version too
5
#7 opened 12 months ago
by 
Gompa