Daniel (Unsloth)'s picture

Daniel (Unsloth) PRO

danielhanchen

·

https://unsloth.ai/

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Tool calling error

updated a model 4 days ago

unsloth/cogito-v2-preview-llama-405B-GGUF

updated a model 4 days ago

unsloth/Qwen3-Coder-30B-A3B-Instruct

View all activity

Organizations

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF 3 days ago

Tool calling error

#1 opened 4 days ago by

New activity in unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF 5 days ago

Please add the IQ1_M 150 GB as one single file for those of us using Ollama without the capacity the model merge using llama cpp locally

#9 opened 5 days ago by

Qwen3-Coder Tool Calling Fixes

#10 opened 5 days ago by

New activity in unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF 5 days ago

Re-uploaded GGUFs with removed <think> tokens for better outputs

#4 opened 5 days ago by

Q4_0 4bit only scored 50.71 on MMLU Pro

#3 opened 5 days ago by

`<think>` and `</think>` missing

#1 opened 5 days ago by

IQ4_NL is generating gibberish on llama.cpp

#2 opened 5 days ago by

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF 6 days ago

Update README.md

#2 opened 6 days ago by

Update README.md

#1 opened 6 days ago by

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507 7 days ago

Update README.md

#1 opened 7 days ago by

New activity in unsloth/Devstral-Small-2507-GGUF 7 days ago

Unsloth template changes broke tool calling

#1 opened 25 days ago by

New activity in unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF 10 days ago

download link creates Q5_K_M instead of UD-Q5_K_XL named files

#2 opened 10 days ago by

New activity in unsloth/Kimi-K2-Instruct-GGUF 13 days ago

144gb vram and 256gb ram

#12 opened 17 days ago by

The correct eos_token_id value for Kimi-K2-Instruct

#11 opened 18 days ago by

New activity in unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF 13 days ago

Best way to offload layers on cPU/RAM for 6x24gb GPU

#4 opened 13 days ago by

Does llama.cpp load 1/4 of parameters work or a program candy?

#5 opened 13 days ago by

New activity in unsloth/Kimi-K2-Instruct-BF16 18 days ago

How did you create it

#1 opened 18 days ago by

New activity in moonshotai/Kimi-K2-Instruct 18 days ago

Correct system prompt?

#28 opened 18 days ago by

New activity in unsloth/Kimi-K2-Instruct-GGUF 21 days ago

Trouble running Q5_K_M With Llama.cpp

#3 opened 21 days ago by

Any Plan for imatrix release of Kimi-K2-Instruct-GGUF

#2 opened 21 days ago by