GLM-4.7 Flash
Z.ai
- Context window
- 203K 202,752 tokens
Timeline
- · Weights version · evidence link
- · Evidence links · GitHub search · Z.ai · commits · localagentbench/Localagentbench · @unknown
- · Evidence links · GitHub search · Z.ai · pulls · vllm-project/vllm · @umarkovi-amd
Excerpt
inactive since #46009. On Radeon Pro W7900 with GLM-4.7-Flash at concurrency 1, this restores 4.5–10.8 % output throughput and 10–13 % TTFT. Related: #46009, #46381
- · Evidence links · GitHub search · Z.ai · pulls · parawanderer/window-ml · @parawanderer
- · Evidence links · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
- · Evidence links · GitHub search · Z.ai · pulls · anomalyco/models.dev · @KevRojo
- · Evidence links · GitHub search · Z.ai · pulls · 1StepMore/AutoMedia · @1StepMore
Specifications
GLM-4.7 Flash is a model from Z.ai with open weights, first recorded on 17 Sep 2026; its release date is not established. The context window is 202,752 tokens.
- Context window
- 202,752
- Weights
- Open
Questions
What is the context window of GLM-4.7 Flash?
The context window is 202,752 tokens.
Are the weights of GLM-4.7 Flash publicly available?
Yes. Z.ai publishes the weights.
When was GLM-4.7 Flash released?
Its release date is not established. Signal Forge first recorded it on 17 Sep 2026.