turboderp

turboderp's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in turboderp/Ling-3.1-flash-exl3 3 days ago

Update README.md

#2 opened 3 days ago by

turboderp

New activity in turboderp/Ling-3.1-flash-exl3 4 days ago

Update README.md

#1 opened 4 days ago by

turboderp

New activity in turboderp/GLM-5.3-Flash-exl3 4 days ago

3.05bpw branch: indexer k-pool compression tensors (index_kpool_compress_ape / _gate) are missing

1

#2 opened 5 days ago by

celikburak

New activity in turboderp/Qwen3.8-Flash-Next-exl3 18 days ago

ngram at bf16?

➕ 1

6

#12 opened about 1 month ago by

nnnig

New activity in turboderp/DeepSeek-V4-Flash-Vision-Exp-exl3 29 days ago

cant make Vision working

3

#1 opened about 1 month ago by

bofff

New activity in turboderp/Qwen3.8-Flash-Next-exl3 about 1 month ago

"All GPUs must be ampere (30 series) or newer."

1

#8 opened about 1 month ago by

laserbeans

Missing vision weights from 2/3/5/6-bit quants?

4

#9 opened about 1 month ago by

HermiHg

New activity in turboderp/Qwen3.8-27B-exl3 about 1 month ago

The quantized vision tower is excellent

1

#10 opened about 1 month ago by

HermiHg

New activity in turboderp/Qwen3.8-Flash-Next-exl3 about 1 month ago

4.05bpw thinking in other languages and/or gibberish

👀 1

5

#5 opened about 1 month ago by

khronnuz

New activity in turboderp/Qwen3.8-Flash-Next-exl3 about 2 months ago

reasoning content not split on Qwen3.8-Flash-Next EXL3 — thinking stays inline in content

3

#4 opened about 2 months ago by

khronnuz

Does this support ngram nvme offloading for people with 32GB system RAM?

4

#3 opened about 2 months ago by

LukeC110

UD_Q4_XL benchmarks ?

1

#1 opened about 2 months ago by

s1arsky

New activity in turboderp/Qwen3.8-27B-exl3 about 2 months ago

Question about Calibration Traces

4

#3 opened about 2 months ago by

Interpause

New activity in brandonmusic/GLM-5.3-Flash-tr3-4bpw about 2 months ago

Independent cross-stack KLD validation using your teacher logits + a public 10.48M-position fidelity suite (and a proposal)

18

#1 opened about 2 months ago by

malaiwah

New activity in turboderp/Qwen3.8-27B-exl3 about 2 months ago

Add recipe.yaml artifacts.

1

#7 opened about 2 months ago by

cloover

Is there a docker way?

2

#6 opened about 2 months ago by

JohnJ990

I love you + self calibrated 6 bit?

➕ 3

1

#4 opened about 2 months ago by

Gaboo

New activity in turboderp/Qwen3.8-27B-exl3 2 months ago

Thank you for your work

👍 8

6

#1 opened 2 months ago by

vonamakitsune

Making sense of the graph

❤️👍 2

1

#2 opened 2 months ago by

spanspek

New activity in turboderp/DeepSeek-V4-Flash-0731-exl3 2 months ago

general

12

#1 opened 2 months ago by

anoane