Michael Han

shimmyshimmer's activity

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

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF 3 days ago

Any reason to not use this model over the 256K context model?

👀 3

3

#1 opened 4 days ago by

mallorbc

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

IQ1 Quant speed issues

1

#7 opened 3 days ago by

DefaultDF

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF 4 days ago

UD-Q4_K_XL and Q5KS

👍 1

2

#2 opened 4 days ago by

AaronFeng753

RooCode Performance Is Very Poor; Thinking & Non Thinking Performing Way Better

16

#4 opened 4 days ago by

JamesMowery

updated a model 4 days ago

unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF

Text Generation • 31B • Updated 4 days ago • 30k • 62

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF 4 days ago

Update README.md

2

#5 opened 4 days ago by

chaoxu-ren

Unsloth's GGUF conversion are all bad ?

👍 1

2

#3 opened 4 days ago by

ijohn07

liked a model 4 days ago

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

Text Generation • 31B • Updated 4 days ago • 102k • 113

updated a collection 4 days ago

Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 43 items • Updated 4 days ago • 166

updated a model 4 days ago

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

Text Generation • 31B • Updated 4 days ago • 102k • 113

liked a model 4 days ago

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

Text Generation • 31B • Updated 4 days ago • 60.4k • 355

published 3 models 4 days ago

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

Text Generation • 31B • Updated 4 days ago • 338 • 8

unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF

Text Generation • 31B • Updated 4 days ago • 30k • 62

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

Text Generation • 31B • Updated 4 days ago • 102k • 113

updated a collection 4 days ago

Qwen3-Coder

Collection

The Qwen3-Coder models deliver SOTA advancements in agentic coding and code tasks. Includes Qwen3-Coder-480B-A35B. • 9 items • Updated 4 days ago • 6

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

Q4_0 4bit only scored 50.71 on MMLU Pro

👀 1

20

#3 opened 5 days ago by

xbruce22

IQ4_NL is generating gibberish on llama.cpp

2

#2 opened 5 days ago by

netroy