Extreme Compression Skeptic Dismisses All Sub-2-Bit Models as Brittle Benchmark-Chasers
teortaxesTex · x · 2026-09-19
X user teortaxesTex argues that all extreme compression models are fundamentally broken: people either explicitly "heal" compression damage with benchmark data or only measure recovery on narrow benchmarks, producing extremely brittle benchsolvers. He dismisses all ≤2-bit post-trained models as slop, a view echoed in replies—reflecting an ongoing debate over ultra-low-bitwidth quantization.
Related event: Extreme low-bit quantized models accused of benchmark gaming(2 posts)→
More from Models
- Dev finds DeepSeek 4.1 Flash faster and cheaper than Gemini Flash — but drops it over data concerns — julianharris · 2026-09-19
- RL-trained classification model Laya trends on Hugging Face — convaiinnovations · 2026-09-19
- OpenAI adds new voices to GPT-Live API, available in developer playground — juberti · 2026-09-19
- DeepSeek v4.1 flash paper figure shows sharp quality jump at 1M-token context — andrew_n_carr · 2026-09-19
- User charged $1,600 for idle containers on OpenAI's new Agents API — Wide-Arugula3042 · 2026-09-19
- Benchmarks show vision models spot image patterns but fail to pick the correct next image — AndrewDai · 2026-09-19