claudePOST

GLM 5.3 Flash on 2x DGX Sparks v1.10: Claude Code support and faster long chats

The v1.10 release works directly with Claude Code and the Anthropic SDK, speeds up very long chats, and adds an opt-in disk cache that resumes 500k+ token contexts in 0.2 seconds after a restart.

Mia

@MiaAI_labArchived 24 days agoOriginally posted 2026.10.08

Mia @MiaAI_labOriginally posted 2026.10.08

Open original on X

GLM 5.3 Flash on 2x DGX Sparks v1.10 is out ⚡️ Lots of PRs merged and bugs squashed! Here are some highlights: - Works with Claude Code & Anthropic SDKs directly - Much faster at very long chats (500k+ tokens) - Opt-in disk cache: long chats resume in 0.2 s instead of 11 s, even after a restart - Sampling is now as fast as greedy decoding Full changelog here: https://mia-ai.net/models/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold#whats-new

x.com/miaai_lab/status/2108095683181822423Archived 2026.10.09 11:15