31 2 258

Full name

TobDeBer

AI & ML interests

Diffusion, Causality, LLM, LMM (Large Music Model), Quantization, AI Context Databases

Recent Activity

liked a model 7 days ago

ostris/Flex.1-alpha

updated a collection 7 days ago

T2I

liked a Space 7 days ago

ostris/Flex.1-alpha

View all activity

Organizations

None yet

TobDeBer's activity

New activity in unsloth/Qwen3-30B-A3B-GGUF about 1 month ago

`UD-Q4_K_XL` or `Q4_K_M`?

#6 opened about 1 month ago by

pootow

New activity in TobDeBer/BPP_Gemma3_1b about 1 month ago

Performance

#1 opened 2 months ago by

robb-0

New activity in unsloth/DeepSeek-V3-0324-GGUF-UD about 1 month ago

Lots of new UD quants

#1 opened about 1 month ago by

segmond

New activity in unsloth/gemma-3-12b-it-GGUF about 1 month ago

Model bigger than regular Q4_K_M. What is the difference then ? (GGUF v2.0)

#6 opened about 1 month ago by

Pumba2

New activity in microsoft/bitnet-b1.58-2B-4T-gguf about 2 months ago

TQ1 quant version

#7 opened about 2 months ago by

TobDeBer

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF about 2 months ago

Which quantized version can run on a Mac computer with 32GB of memory?

#2 opened about 2 months ago by

jimpunk

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct 2 months ago

DOA

👍 1

#1 opened 2 months ago by

MrDevolver

New activity in unsloth/DeepSeek-V3-0324-GGUF 2 months ago

Is the 2.51bit model using imatrix?

#3 opened 2 months ago by

daweiba12

New activity in unsloth/Qwen2.5-14B-Instruct-unsloth-bnb-4bit 3 months ago

Dynamic bnb-4bit

👍 1

#1 opened 3 months ago by

iqdddd

New activity in unsloth/DeepSeek-R1-GGUF 3 months ago

RTX 5090 with 600GB of RAM what models？

#40 opened 3 months ago by

frank-mx

New activity in unsloth/DeepSeek-R1-GGUF 4 months ago

Accuracy of the dynamic quants compared to usual quants?

#21 opened 4 months ago by

inputout

New activity in unsloth/Llama-3.2-11B-Vision-unsloth-bnb-4bit 4 months ago

Saving to q5_k_m GGUF

#1 opened 4 months ago by

sasha1234567

New activity in unsloth/DeepSeek-R1-GGUF 4 months ago

8bits quantization

#20 opened 4 months ago by

ramkumarkoppu

Is there a model removing non-shared MoE experts?

#17 opened 4 months ago by

ghostplant

Over 2 tok/sec agg backed by NVMe SSD on 96GB RAM + 24GB VRAM AM5 rig with llama.cpp

🔥 👍 4

#13 opened 4 months ago by

ubergarm

Quantizer Tool

#14 opened 4 months ago by

TobDeBer

Where did the BF16 come from?

#10 opened 4 months ago by

gshpychka

New activity in unsloth/Llama-3.1-Nemotron-70B-Instruct-bnb-4bit 7 months ago

vram+ram

#7 opened 7 months ago by

sdyy

New activity in unsloth/Qwen2.5-Coder-32B 7 months ago

Colab

#1 opened 7 months ago by

Srrp

New activity in unsloth/Llama-3.2-3B-Instruct-GGUF 8 months ago

11b instruct gguf?

➕ 😔 2

#1 opened 8 months ago by

celsowm