Zxbc

zxbc2023's activity

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

New activity in bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF 23 days ago

Possible to strip MTP layer?

👍 1

2

#5 opened about 2 months ago by

jcmyang750

New activity in OrionLLM/GRM-3.2-Sky about 1 month ago

Any update in the pipeline?

👍 1

3

#6 opened about 1 month ago by

zxbc2023

New activity in ornith-ai/Ornith-1.5-35B-A3B about 1 month ago

Best local model that runs on commodity hardware

😔 1

22

#23 opened about 1 month ago by

dwidlee

Low quality and gaslighting

1

#20 opened about 1 month ago by

I-Am-Sam

model-00016-of-00016.safetensors was just updated... What?

3

#25 opened about 1 month ago by

pathosethoslogos

Investigating the Trade-off between Reasoning/Efficiency and Instruction Following in Ornith-1.5

👍 1

16

#26 opened about 1 month ago by

AnbaiMei

Great work. Bad advertisement.

👍 5

2

#17 opened about 1 month ago by

Izenflamm

No speculative decoding, No QAT

8

#21 opened about 1 month ago by

engrtipusultan

New activity in TeichAI/Qwen3.8-27B-Fable-Distill-GGUF about 1 month ago

in my local heavy agentic work your model is way better

❤️ 3

3

#2 opened about 1 month ago by

ntoytoy

New activity in incoai/Qwen3.8-27B-DFlash2-GGUF about 1 month ago

Code acceptance rate and token speed drops on write tool calls in pi coding agent

👍➕ 3

6

#3 opened about 1 month ago by

sandeshrajx

New activity in ornith-ai/Ornith-1.5-35B-A3B about 1 month ago

Seems to perform worse than 1.0

👍 2

1

#13 opened about 1 month ago by

russellcg

mtp.* tensors look like random init, not trained weights

🧠👍 9

17

#10 opened about 1 month ago by

EryriLabs

New activity in bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF about 1 month ago

Decided to close the discussion because its better to email privately the hf staff. Bye

🧠🤯 3

14

#3 opened about 1 month ago by

seadownfallpioneer10

New activity in z-lab/Qwen3.8-27B-DFlash2 about 1 month ago

Yet to see any gains from DFlash

👍 11

13

#3 opened about 1 month ago by

Dnonmi

New activity in ornith-ai/Ornith-1.5-35B-A3B about 1 month ago

Use DFlash instead of MTP and stop wasting time

👍 4

2

#11 opened about 1 month ago by

zxbc2023

New activity in mradermacher/Qwen3.8-27B-Fable-Distill-i1-GGUF about 1 month ago

Incorrect answer to simple arithmetic question on the i1-Q4_K_S imatrix quant

#1 opened about 1 month ago by

zxbc2023

New activity in incoai/Qwen3.8-27B-DFlash2-GGUF about 1 month ago

Q4_K_M wrong number of tensors; expected 81, got 58

➕ 5

4

#4 opened about 1 month ago by

JMorris1999

Isn't it think too much?

6

#1 opened about 1 month ago by

emircanerkul

New activity in DimInfer/Qwen3.8-27B-Dspark-v1 about 2 months ago

can you upload a smaller sized quant like q4_k_xl or q5_k_xl? or i matrix

2

#2 opened about 2 months ago by

ahmedsevenup

Beats native MTP head by 10-20% across the board

➕ 2

3

#1 opened about 2 months ago by

zxbc2023