Tariel

Tariel's activity

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

New activity in mudler/Ornith-1.5-35B-A3B-APEX-MTP-GGUF 5 days ago

Default MTP layers of Ornith-1.5-35B-A3B have low acceptance

7

#3 opened 12 days ago by

Tariel

New activity in peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP 5 days ago

APEX quant version please

2

#7 opened 6 days ago by

Tariel

commented a paper 9 days ago

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 95 •

8

New activity in ByteDance-Seed/Seed-OSS-36B-Instruct 9 days ago

Whis a dflash speculative decoding model for Seed-OSS-36B-Instruct

#34 opened 9 days ago by

Tariel

New activity in tencent/Hy-MT2-30B-A3B 10 days ago

Max context length

1

#6 opened 10 days ago by

Tariel

New activity in ornith-ai/Ornith-1.5-35B-A3B 10 days ago

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

🧠👍 9

15

#10 opened 12 days ago by

EryriLabs

New activity in ggufbench/Qwen3.6-27B-4bpw-16GB-VRAM 17 days ago

Wish a Qwen3.8-27B version

#5 opened 17 days ago by

Tariel

New activity in Qwen/Qwen-AgentWorld-35B-A3B 2 months ago

"no MTP"

👍 3

3

#3 opened 2 months ago by

laserbeans

Great on HERMES! Noob Question

➕ 2

4

#8 opened 2 months ago by

GravyLuver

New activity in mudler/Qwen3.6-35B-A3B-APEX-GGUF 2 months ago

Wish an APEX quantized version of Qwen/Qwen-AgentWorld-35B-A3B

#15 opened 2 months ago by

Tariel

New activity in Qwen/Qwen-AgentWorld-35B-A3B 2 months ago

Misunderstood what it is for, but it works super good with Openclaw, wtf?!

👍 8

1

#9 opened 2 months ago by

Wladastic

compatible mmproj from Qwen3.6-35B-A3B

👍 5

3

#7 opened 2 months ago by

C0d3B0dy

"no MTP"

👍 3

3

#3 opened 2 months ago by

laserbeans

compatible mmproj from Qwen3.6-35B-A3B

👍 5

3

#7 opened 2 months ago by

C0d3B0dy