Abliterated Qwen3.8-Flash GGUF quants land on Hugging Face
SC117 · hf · 2026-10-06
HF user SC117 released Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF, an uncensored (abliterated) quantized build for llama-cpp, tagged with GSQ/RCO quantization, tensor-transplant and MoE. Aimed at local deployments wanting fewer guardrails.
More from Models
- Claude remains ~2.5x more efficient in token/plan comparison, blogger claims — kimmonismus · 2026-10-06
- Beam's benchmarks disappoint: US open model lags Chinese rivals like DeepSeek, says Reddy — bindureddy · 2026-10-06
- Model Census pings every listed LLM daily to track availability and deprecations — repligate · 2026-10-06
- Prediction: Claude to launch hosting service so its generated apps deploy on Claude Cloud — ThePeterMick · 2026-10-06
- Burkov on GPT 6.1: 'I can describe it in one word: slow' — burkov · 2026-10-06
- Dev says GLM5.3 is the only model 'willing to protect my app and my users' — lucasmeijer · 2026-10-06