Full name
TobDeBer
AI & ML interests
Diffusion, Causality, LLM, LMM (Large Music Model), Quantization, AI Context Databases
Recent Activity
updated
a Space
4 days ago
TobDeBer/BPP_Gemma3_1b
liked
a Space
4 days ago
bnb-community/bnb-my-repo
updated
a Space
4 days ago
TobDeBer/Upstream_Gemma3_1b
Organizations
None yet
TobDeBer's activity
Dynamic bnb-4bit
2
#1 opened 19 days ago
by
iqdddd
RTX 5090 with 600GB of RAM what modelsοΌ
4
#40 opened 25 days ago
by
frank-mx
Accuracy of the dynamic quants compared to usual quants?
19
#21 opened about 1 month ago
by
inputout

Saving to q5_k_m GGUF
4
#1 opened about 1 month ago
by
sasha1234567
8bits quantization
5
#20 opened about 2 months ago
by
ramkumarkoppu
Is there a model removing non-shared MoE experts?
4
#17 opened about 2 months 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 about 2 months ago
by
ubergarm
Quantizer Tool
2
#14 opened about 2 months ago
by
TobDeBer
Where did the BF16 come from?
8
#10 opened about 2 months ago
by
gshpychka
vram+ram
4
#7 opened 5 months ago
by
sdyy
11b instruct gguf?
3
#1 opened 6 months ago
by
celsowm

Why is it called 1.0b?
#4 opened 6 months ago
by
TobDeBer
Apply for community grant: Personal project (gpu)
#1 opened 6 months ago
by
TobDeBer
torch and llama.cpp integration
3
#1 opened 6 months ago
by
TobDeBer
Fine control for Turbo and Lightning models
1
#1 opened 7 months ago
by
TobDeBer
Please provide ggml variants for local execution
1
#3 opened 8 months ago
by
TobDeBer
Please host on zero
#2 opened 8 months ago
by
TobDeBer
RuntimeError: cutlassF: no kernel found to launch!
12
#11 opened about 1 year ago
by
mayonaisu
Better example code?
9
#13 opened about 1 year ago
by
Softology