487 22 285

Michael Han

shimmyshimmer

https://unsloth.ai

AI & ML interests

None yet

Recent Activity

updated a collection about 1 hour ago

Qwen3-Coder

updated a collection about 1 hour ago

Qwen3-Coder

updated a collection about 1 hour ago

Qwen3-Coder

View all activity

Organizations

New activity in unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF about 4 hours ago

Q4_0 4bit only scored 50.71 on MMLU Pro

👀 1

#3 opened about 9 hours ago by

xceptor

New activity in unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF about 16 hours ago

IQ4_NL is generating gibberish on llama.cpp

#2 opened about 20 hours ago by

netroy

New activity in unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF about 21 hours ago

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

👀 2

#1 opened about 21 hours ago by

johnbean393

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF 2 days ago

Update README.md

#2 opened 2 days ago by

shimmyshimmer

Update README.md

#1 opened 2 days ago by

shimmyshimmer

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507 2 days ago

Update README.md

#2 opened 2 days ago by

shimmyshimmer

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507 3 days ago

Update README.md

#1 opened 3 days ago by

shimmyshimmer

New activity in unsloth/GLM-4.1V-9B-Thinking-GGUF 4 days ago

endless response

👀 👍 4

#2 opened 6 days ago by

thettalos

New activity in unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF 6 days ago

I-quants?

#1 opened 6 days ago by

tarruda

New activity in unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF 6 days ago

UD-Q4_K_XL matches bf16 with 60.9% vs 61.8% on Aider Polyglot benchmark

🔥 👍 7

#8 opened 6 days ago by

Fernanda24

New activity in unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF 7 days ago

Would there by bnb version for the UD quants?

#5 opened 7 days ago by

Sandbo

New activity in mistralai/Magistral-Small-2507 7 days ago

Add Unsloth for Magistral fine-tuning support

#3 opened 7 days ago by

shimmyshimmer

New activity in unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF 7 days ago

Perplexity Benchmarks

#7 opened 7 days ago by

thad0ctor

New activity in unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF 7 days ago

Missing UD-Q5_K_XL

#4 opened 7 days ago by

Aver0

New activity in unsloth/Kimi-K2-Instruct-GGUF 8 days ago

Amazing quality in such low Q4 on 2014 ANCIENT Xeon CPU with just shy 582Gb RAM

❤️ 2

#15 opened 10 days ago by

krustik

New updates: Correct system prompt, Tool calling, more fixes & llama.cpp!

🚀 ❤️ 3

#7 opened 14 days ago by

shimmyshimmer

New activity in unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF 8 days ago

What about ternary? =D

❤️ 🧠 2

#6 opened 8 days ago by

BahamutRU

4bit works great. thanks.

🤗 1

#3 opened 8 days ago by

jeffwadsworth

How to use GGUF in sglang or vllm?

#2 opened 8 days ago by

hermitg

New activity in unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF 9 days ago

TQ1_0 Quant?

#2 opened 9 days ago by

QuietImpostor

Michael Han

AI & ML interests

Recent Activity

Organizations

shimmyshimmer's activity

Q4_0 4bit only scored 50.71 on MMLU Pro

IQ4_NL is generating gibberish on llama.cpp

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

Update README.md

Update README.md

Update README.md

Update README.md

endless response

I-quants?

UD-Q4_K_XL matches bf16 with 60.9% vs 61.8% on Aider Polyglot benchmark

Would there by bnb version for the UD quants?

Add Unsloth for Magistral fine-tuning support

Perplexity Benchmarks

Missing UD-Q5_K_XL

Amazing quality in such low Q4 on 2014 ANCIENT Xeon CPU with just shy 582Gb RAM

New updates: Correct system prompt, Tool calling, more fixes & llama.cpp!

What about ternary? =D

4bit works great. thanks.

How to use GGUF in sglang or vllm?

TQ1_0 Quant?