708-145 PRO
TobDeBer
AI & ML interests
Diffusion, Causality, LLM, LMM (Large Music Model), Quantization, AI Context Databases
Recent Activity
new activity about 2 hours ago
unsloth/Qwen3.5-9B-MTP-GGUF:Is using MTP actually slower? new activity about 11 hours ago
unsloth/GLM-5.2-GGUF:Is it possible to make less than 1 bit quantization? updated a model 13 days ago
TobDeBer/M8Organizations
None yet
spaces 14
pinned
Build error
Agents
3
2026 - Music Descriptor CPU
🚀
CPU version
pinned
Sleeping
Agents
1
Black Forest Lab's FLUX.2[dev]7step
😻
7-step turbo FLUX.2 by fal and TobDeBer
pinned
Sleeping
Agents
1
SmolTransform
🐢
Use Smollm with transformer for inference
pinned
Running on Zero
Agents
3
Granite4 Family
🌖
Chat: Granite4 family
pinned
Sleeping
Agents
Refine RealVis
⚡
Refiner with REALVISXL V5.0 + LIGHTNING
Sleeping
Agents
Granite 4 extreme T3
📝
Chat with Granite4
models 28
TobDeBer/M8
Updated
TobDeBer/Mellum2-12B-A2.5B-Instruct-Q3_K_L-GGUF
Text Generation • 12B • Updated • 134
TobDeBer/Olmo-3.1-32B-Instruct-magic1-Q6_K-GGUF
32B • Updated • 224
TobDeBer/Olmo-3.1-32B-Instruct-magic1
Text Generation • 32B • Updated • 31
TobDeBer/maegic
Updated • 4
TobDeBer/SmolLM2-135M-Instruct-magic1
Text Generation • 0.1B • Updated • 4
TobDeBer/SmolLM2-135M-Instruct-magic1-Q6_K-GGUF
Text Generation • 0.1B • Updated • 18
TobDeBer/SmolLM2-135M-Instruct-hirma-b60s-0.5
Text Generation • 99.6M • Updated • 3
TobDeBer/SmolLM3-3B-hirma-b100-0.5
Text Generation • 4B • Updated • 2
TobDeBer/SmolLM2-135M-Instruct-b100s
0.2B • Updated • 5
datasets 0
None public yet