2-bit Quantized Qwen 35B Evaluated on Terminal-Bench for Agentic Coding
DavidBennett__ · x · 2026-07-31
An independent team evaluated Escha Labs' 2-bit quantized Qwen 3.6 35B model on Terminal-Bench 2.1, a benchmark for agentic coding. The results show that the extreme low-bit quantized model remains viable. Further tests will be conducted at longer context lengths, such as 128K, to assess quantization quality preservation.
More from Models
- Luna Offers Cheaper Inputs, but DeepSeek Wins Cache Economics in Long Agentic Sessions — teortaxesTex · 2026-07-31
- User Criticizes Hive AI: Fake Image Missed, Fake Sound Detected in Silent Clip — henkvaness · 2026-07-31
- DeepSWE Coding Agent Leaderboard: Claude Opus and GPT-5.6 Top the Charts — tristanbob · 2026-07-31
- Hive AI Detection Fails: Fake Crows Missed, 36% Music Detected in Silent Clip — henkvaness · 2026-07-31
- Google Responds to AI Misinformation Concerns: Gemini Images Embed SynthID Watermarks — henkvaness · 2026-07-31
- Users report OpenAI's o1-pro model got slower but smarter — teortaxesTex · 2026-07-31