Strata runs 125B Qwen3.8-Flash-Next on a 16GB consumer GPU
evilsocket · x · 2026-10-01
evilsocket demos running Qwen3.8-Flash-Next (125B params, IQ1M quantization) on a single 16GB NVIDIA GPU with the open-source Strata inference engine. Highlights: one-click install on Windows/Linux needing a 12-24GB GPU plus 64GB RAM, 60-95 tokens/s output, local OpenAI/Anthropic-compatible APIs, optional image input, and 3.9k GitHub stars.
More from Infra
- Ascend output could hit ~20M chips next year; memory and packaging, not logic, are the bottleneck — teortaxesTex · 2026-11-19
- AMD Loom boosts Qwen3.5-4B prefill up to 2.6x on Radeon 890M laptops — jfowers_amd · 2026-11-19
- Dev submits PR adding periodic checkpoints to GKE sandboxes so agents don't lose progress — yoimnotkesku · 2026-11-19
- AWS Lambda Adds GPU Support via Managed Instances for Inference and Media Workloads — DavidWells · 2026-11-19
- Nvidia Allegedly Made GPUs Artificially Scarce to Keep Prices Sky-High — GaryMarcus · 2026-11-19
- AWS adds private CA support to Bedrock AgentCore Identity for connecting agents to self-hosted IdPs — AWS ML Blog · 2026-11-19