Strata 0.2.11 ships Unsloth Dynamic v3.1 quants, 1-bit runs at 68GB
danielhanchen · x · 2026-11-05
Local inference app Strata released v0.2.11, and Unsloth's Daniel Hanchen confirms the new Dynamic v3.1 quants run seamlessly: seven 1-4bit GGUF tiers of Qwen3.8-Flash-Next (UD-IQ1M at 68GB up to UD-IQ4XS-v31 at 93.7GB, sharing 28.8GB lookup tables, SHA-256 verified) plus UD v3.1 DeepSeek-V4.1-Flash GGUFs. The release also adds prompt-speed improvements on NVIDIA/Radeon, small multi-GPU starts, chat saving, and DGX Spark support.
Related event: Strata 0.2.11 adds Unsloth Dynamic v3.1 quantization support(2 posts)→
More from Infra
- Google's 1999 server rack: wooden shelves, tangled cables, and a lesson in just building — Yamapama · 2026-11-05
- Olki ditches LLM-based agent monitoring for strict type systems and effects algebra — bigdata · 2026-11-05
- tiny-llm: Open Course Builds a Mini vLLM Inference Engine on Apple Silicon — alexcovo_eth · 2026-11-05
- DeepSeek charges double for peak-hour API calls, and off-peak scheduling halves your token bill — AccBalanced · 2026-11-05
- NVIDIA RTX PRO 5500 Blackwell lists at $17,999, pricier than RTX PRO 6000's $16,000 — panchovix · 2026-11-05
- Nemotron 3.5 Bolt E4B hits 27.7 tok/s on Jetson Nano, 1.8x faster than llama.cpp — Course_Latter · 2026-11-05