708-145 PRO
TobDeBer
AI & ML interests
Diffusion, Causality, LLM, LMM (Large Music Model), Quantization, AI Context Databases
Recent Activity
updated a model 1 day ago
TobDeBer/maegic liked a model 5 days ago
microsoft/Fara-7B updated a model 5 days ago
TobDeBer/M8Organizations
None yet
Gemma 4 MTP assistant/drafter models in GGUF
1
#41 opened 5 days ago
by
redLiw
Model does not support audio
👍 3
4
#1 opened about 1 month ago
by
alphamerian
Update app.py
#1 opened 4 months ago
by
TobDeBer
Should UD-Q6_K_XL identical to Q6_K.gguf?
5
#1 opened 6 months ago
by
BVEsun
BF16 or Q8_K_XL - which would give more accurate coding results?
5
#6 opened 6 months ago
by
TimothyRoo
Jan 12 2026: Qwen3-Next updated with iMatrix + Improved performance!
👍 3
26
#3 opened 6 months ago
by
danielhanchen
Benchmark suggestion
2
#2 opened 6 months ago
by
FlareRebellion
Layer bumping is very similar to unsloth dynamic quant
1
#1 opened 6 months ago
by
TobDeBer
Perplexity Benchmarks
3
#7 opened 10 months ago
by
thad0ctor
Pls MXFP4
🔥 1
5
#4 opened 7 months ago
by
Kirara702
Can we create a ..."GLM-4.6-Distill-GLM-4.5-Air-GGUF"?
3
#13 opened 8 months ago
by
NKLAR5
Will you create the dynamic quants for this model?
2
#1 opened 9 months ago
by
snapo
size matters.
👍 1
1
#5 opened 9 months ago
by
LeroyDyer
iq2_bn with 4 or 5 weights per byte?
#2 opened 11 months ago
by
TobDeBer
`UD-Q4_K_XL` or `Q4_K_M`?
16
#6 opened about 1 year ago
by
pootow
Lots of new UD quants
2
#1 opened about 1 year ago
by
segmond
Model bigger than regular Q4_K_M. What is the difference then ? (GGUF v2.0)
2
#6 opened about 1 year ago
by
Pumba2
TQ1 quant version
3
#7 opened about 1 year ago
by
TobDeBer