JM

akierum's activity

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

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B 7 days ago

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

9

#9 opened 15 days ago by

akierum

New activity in deepreinforce-ai/Ornith-1.0-35B-GGUF 9 days ago

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

👍 1

33

#22 opened 25 days ago by

Sdoh

New activity in migtissera/Tess-4-27B 11 days ago

maximum context length

2

#12 opened 11 days ago by

darvec

Started deleting my stuff?

2

#5 opened 14 days ago by

jamiem90

New activity in protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-GGUF 11 days ago

please provide vision mmproj file

🤝 1

4

#4 opened 15 days ago by

akierum

New activity in bartowski/nex-agi_Nex-N2-mini-GGUF 14 days ago

Fails with using chrome dev tools Take screenshot

#4 opened 14 days ago by

akierum

New activity in protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-GGUF 14 days ago

Janai imports model with wrong name

3

#6 opened 15 days ago by

akierum

New activity in unsloth/Qwen3.6-27B-GGUF 15 days ago

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

#32 opened 15 days ago by

akierum

New activity in protoLabsAI/ThinkingCap-Qwen3.6-27B-MTP-GGUF 15 days ago

Thanks for this

🤗 1

1

#5 opened 15 days ago by

jcbtc

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

2

#3 opened 15 days ago by

akierum

New activity in InternScience/Agents-A1-Q8_0-GGUF 16 days ago

codeneedle has bad results

2

#3 opened 20 days ago by

akierum

New activity in mudler/Agents-A1-APEX-GGUF 19 days ago

So is this better then original Q8 version

#2 opened 19 days ago by

akierum

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

included jinja template wrong default parameters why?

1

#2 opened 20 days ago by

akierum

No vision support where is mmproj file?

4

#1 opened 20 days ago by

akierum

New activity in deepreinforce-ai/Ornith-1.0-35B-GGUF 20 days ago

Can not use 35B with claude code and codex.

2

#19 opened 25 days ago by

beginor

Aider Polyglot Benchmark Results (C++ & Python) — Q4 through Q8

👍 4

4

#23 opened 25 days ago by

YukiTomita-CC

New activity in froggeric/Qwen-Fixed-Chat-Templates 26 days ago

Breaks claude code

13

#41 opened about 1 month ago by

widdae

New activity in deepreinforce-ai/Ornith-1.0-35B-GGUF 26 days ago

31B-Dense model missing from HuggingFace

👍👀 28

15

#2 opened 28 days ago by

smcleod

New activity in deepreinforce-ai/Ornith-1.0-35B 27 days ago

Very impressive with openclaw! and fixed chat template by Opus

🔥 1

5

#11 opened 28 days ago by

Andy5k

New activity in deepreinforce-ai/Ornith-1.0-35B-GGUF 27 days ago

Does Ornith-1.0-35B preserve historical reasoning traces like Qwen3.6?

1

#11 opened 27 days ago by

eflaneble