Qwen3-Coder-Next-GGUF
- Home
- / Recommended Models
- / Qwen3-Coder-Next-GGUF
Qwen3-Coder-Next-GGUF
VRAM needed
≈ 24 GB
Fits 24 GB+ consumer GPUs
Authorunsloth
Parameters80B
QuantizationUD-IQ2_XXS
FormatGGUF
Licenseapache-2.0
File size21.71 GB
Overview
Qwen3-Coder Next 80B at an aggressive 2-bit quant - frontier-class coding quality that still fits a 24 GB GPU via heavy quantization.
Recommended hardware
≈ 24 GB VRAM to run this 80B model at the UD-IQ2_XXS quantization.
Fits 24 GB+ consumer GPUs (e.g. RTX 3090, RTX 4090)