JM

akierum's activity

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

New activity in Kwaipilot/KAT-Coder-V2.5-Dev about 23 hours ago

What are best llamma.cpp run settings for opencode etc.?

3

#9 opened 3 days ago by

akierum

New activity in Kwaipilot/KAT-Coder-V2.5-Dev 3 days ago

MTP support? Why no Vision?

18

#3 opened 5 days ago by

unoid

New activity in poolside/Laguna-XS-2.1-GGUF 3 days ago

Pretty good

👍 2

7

#2 opened 8 days ago by

flyingweasel

No Vision where is mmproj file

#3 opened 3 days ago by

akierum

New activity in inclusionAI/LLaDA2.2-flash 3 days ago

Mini Model?

2

#1 opened 4 days ago by

Akicou

New activity in owao/Nanbeige4.2-3B-GGUF 3 days ago

llama tool calling

👍🤗 3

4

#2 opened 4 days ago by

xenarathon

New activity in Kwaipilot/KAT-Coder-V2.5-Dev 4 days ago

Q8 version Loops

2

#8 opened 4 days ago by

akierum

codeneedle results

👍 4

4

#7 opened 4 days ago by

akierum

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B 11 days ago

ThinkingCap-Qwen3.6-27B - Without Q8_XL Quant to match Unsloth this is waste of time sorry.

9

#9 opened 20 days ago by

akierum

New activity in deepreinforce-ai/Ornith-1.0-35B-GGUF 14 days ago

Reasoning degradation and tool calling failures at 70-80K context tokens

👍 1

33

#22 opened 29 days ago by

Sdoh

New activity in migtissera/Tess-4-27B 15 days ago

maximum context length

2

#12 opened 15 days ago by

darvec

Started deleting my stuff?

2

#5 opened 19 days ago by

jamiem90

New activity in protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-GGUF 16 days ago

please provide vision mmproj file

🤝 1

4

#4 opened 20 days ago by

akierum

New activity in bartowski/nex-agi_Nex-N2-mini-GGUF 18 days ago

Fails with using chrome dev tools Take screenshot

#4 opened 18 days ago by

akierum

New activity in protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-GGUF 18 days ago

Janai imports model with wrong name

3

#6 opened 19 days ago by

akierum

New activity in unsloth/Qwen3.6-27B-GGUF 19 days ago

Why LMstudio downbloads mmproj-F32.gguf instead of mmproj-F16.gguf for Q8 ?

#32 opened 19 days ago by

akierum

New activity in protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-GGUF 19 days ago

Thanks for this

🤗 1

1

#5 opened 20 days ago by

jcbtc

New activity in protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-GGUF 20 days ago

Q8 seems best version tested so far even better than unsloth Q8_XL compared by codeneedle

2

#3 opened 20 days ago by

akierum

New activity in InternScience/Agents-A1-Q8_0-GGUF 20 days ago

codeneedle has bad results

2

#3 opened 24 days ago by

akierum

New activity in mudler/Agents-A1-APEX-GGUF 23 days ago

So is this better then original Q8 version

#2 opened 23 days ago by

akierum