unsloth
/

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

Text Generation

Model card Files Files and versions

Resources

View closed (6)

New Refresh with added Tool Calling in calibration dataset and improved imatrix

#21 opened 10 days ago by

New Chat Template + Tool Calling Fixes as of 05 Aug, 2025

#10 opened 6 months ago by

the Qwen3-Coder-30B-A3B-Instruct-UD-IQ3_XXS.gguf is amazing on my RTX 5060 TI.

#19 opened 26 days ago by

Thank you very much! Phenomenal on old hardware.

#18 opened 2 months ago by

Confusion between FP16 and BF16

#17 opened 3 months ago by

IQ4_NL 17.3 GB and OLLAMA_KV_CACHE_TYPE' -Value 'q8_0' Gibber after certain 100k context

#16 opened 4 months ago by

Working with Cline

#14 opened 5 months ago by

Is the Q8_0 derived from the official FP8?

#13 opened 5 months ago by

Updated Title: UDQ4_K_XL - Great Rust coder

#11 opened 6 months ago by

wonderfuldestruction

实在不行模拟数据，使每一个图都要能够可视化，同时要求指标显着于8个，业务解读明显于6条。文本和图要注意多，大概正片下来有10000字左右，且可视化图表最少8个。给出我最后改善后的html

#9 opened 6 months ago by

Create study tools

#8 opened 6 months ago by

IQ1 Quant speed issues

#7 opened 6 months ago by

Updated Jinja for LM Studio MCP tool calls - tools with no required params or other weirdly defined mcp tools

#6 opened 6 months ago by

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

#4 opened 6 months ago by

Tool calling error

#1 opened 6 months ago by