Full name
TobDeBer
AI & ML interests
Diffusion, Causality, LLM, LMM (Large Music Model), Quantization, AI Context Databases
Recent Activity
updated
a collection
4 days ago
T2I
liked
a Space
4 days ago
multimodalart/flux-fill-outpaint
new activity
5 days ago
unsloth/DeepSeek-R1-GGUF:Is there a model removing non-shared MoE experts?
Organizations
None yet
TobDeBer's activity
Is there a model removing non-shared MoE experts?
4
#17 opened 6 days ago
by
ghostplant
Over 2 tok/sec agg backed by NVMe SSD on 96GB RAM + 24GB VRAM AM5 rig with llama.cpp
9
#13 opened 9 days ago
by
ubergarm
Quantizer Tool
2
#14 opened 8 days ago
by
TobDeBer
Where did the BF16 come from?
8
#10 opened 9 days ago
by
gshpychka
vram+ram
4
#7 opened 3 months ago
by
sdyy
11b instruct gguf?
3
#1 opened 4 months ago
by
celsowm
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63a278c3f30c4642278d4259/W0U2_asElVWplHF6sLsDf.png)
Why is it called 1.0b?
#4 opened 4 months ago
by
TobDeBer
Apply for community grant: Personal project (gpu)
#1 opened 4 months ago
by
TobDeBer
torch and llama.cpp integration
3
#1 opened 5 months ago
by
TobDeBer
Fine control for Turbo and Lightning models
1
#1 opened 6 months ago
by
TobDeBer
Please provide ggml variants for local execution
1
#3 opened 6 months ago
by
TobDeBer
Please host on zero
#2 opened 6 months ago
by
TobDeBer
RuntimeError: cutlassF: no kernel found to launch!
12
#11 opened 12 months ago
by
mayonaisu
Better example code?
9
#13 opened 12 months ago
by
Softology
Lower RAM requirements
#10 opened 12 months ago
by
TobDeBer
add negative prompt
#3 opened 12 months ago
by
TobDeBer