Daniel (Unsloth)'s picture

Daniel (Unsloth) PRO

danielhanchen

·

https://unsloth.ai/

AI & ML interests

None yet

Recent Activity

updated a model 1 day ago

unsloth/grok-2-GGUF

updated a model 2 days ago

unsloth/grok-2

updated a model 2 days ago

unsloth/grok-2

View all activity

Organizations

New activity in unsloth/DeepSeek-V3.1-GGUF 17 days ago

Please upload the Q8_0 variant.

#3 opened 17 days ago by

Thanks!

#1 opened 18 days ago by

New activity in unsloth/gpt-oss-20b-BF16 about 1 month ago

Clarification needed: Are the FP16 weights original or upconverted from 4-bit?

#1 opened about 1 month ago by

New activity in unsloth/gpt-oss-20b-GGUF about 1 month ago

GGUF uploaded now + Chat template Fixes!

#2 opened about 1 month ago by

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF about 1 month ago

Tool calling error

#1 opened about 1 month ago by

New activity in unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF about 1 month 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 about 1 month ago by

Qwen3-Coder Tool Calling Fixes

#10 opened about 1 month ago by

New activity in unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF about 1 month ago

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

#4 opened about 1 month ago by

Q4_K_M 4bit only scored 80.00 on MMLU Pro

#3 opened about 1 month ago by

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

#1 opened about 1 month ago by

IQ4_NL is generating gibberish on llama.cpp

#2 opened about 1 month ago by

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF about 1 month ago

Update README.md

#2 opened about 1 month ago by

Update README.md

#1 opened about 1 month ago by

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507 about 1 month ago

Update README.md

#1 opened about 1 month ago by

New activity in unsloth/Devstral-Small-2507-GGUF about 1 month ago

Unsloth template changes broke tool calling

#1 opened about 2 months ago by

New activity in unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF about 1 month ago

download link creates Q5_K_M instead of UD-Q5_K_XL named files

#2 opened about 1 month ago by

New activity in unsloth/Kimi-K2-Instruct-GGUF about 2 months ago

144gb vram and 256gb ram

#12 opened about 2 months ago by

The correct eos_token_id value for Kimi-K2-Instruct

#11 opened about 2 months ago by

New activity in unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF about 2 months ago

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

#4 opened about 2 months ago by

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

#5 opened about 2 months ago by