Unsloth's new quantization makes local Qwen Flash Next feel almost like Qwen4
danielhanchen · x · 2026-11-12
Japanese user @ryu15 reports that Unsloth's new quantization (Qwen3.8 Flash Next UD IQ4XS) runs impressively well locally, joking it could just be called Qwen4. The attached screenshot shows a voxel-style Japanese pagoda garden demo rendered with the model.
After trying Qwen4 Max Preview, the author revisited the local quantized model and found Unsloth's recent quantization work remarkably strong.
More from Models
- Which Claude model for which job: a 5-scenario real-work comparison — petergyang · 2026-11-12
- Zvi 周报:METR 加速报告引发 2027 智能爆炸预期大幅更新 — Don't Worry About the Vase (Zvi) · 2026-11-12
- Anthropic user shows off 4 free limit resets: one full reset plus three Fable resets — zsakib_ · 2026-11-12
- Raon-1 Nano 3.1B gets native ik_llama.cpp runtime with 17% faster MTP speculative decoding — Any_Bus9205 · 2026-11-12
- New complexity paper claims more reasoning tokens strictly expand what transformers can solve; critics push back — gerardsans · 2026-11-12
- LibreAGI: A New Project to Save Open-Weights OSS Models — satuke · 2026-11-12