Z.ai released GLM-4.7, an open-weight model available on Cerebras Inference Cloud that achieves approximately 1,000 tokens per second and up to 1,700 TPS for specific use cases.
GLM-4.7 introduces preserved thinking, allowing reasoning context to persist across turns.
The model interleaves thinking before each action, tool call, or response rather than treating reasoning as a single upfront step.
cerebras.ai2026-01-089 HN pts · 1 comments748 wordsabout the GLM 4 family family
3 best of 3 tracked
The 1 pick above, plus these 2. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; 8 quantized builds for local use.
Everything else, folded: the full tables, every source.
Use-case evidence
4 use cases
What it is good at 4 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Hosted endpoints observed for GLM-4-32B-0414, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
cerebras.ai2026-01-08about the GLM 4 familyHN 9 pts · 1 comments748 words
Z.ai released GLM-4.7, an open-weight model available on Cerebras Inference Cloud that achieves approximately 1,000 tokens per second and up to 1,700 TPS for specific use cases. The model delivers roughly 10x higher price-performance than Claude Sonnet 4.5 while maintaining comparable intelligence to DeepSeek-V3.2 on developer benchmarks. Teams can access the model via Cerebras Cloud starting at a $10 pay-as-you-go developer tier.written, reviewed, cited
GLM-4.7 introduces preserved thinking, allowing reasoning context to persist across turns.
The model interleaves thinking before each action, tool call, or response rather than treating reasoning as a single upfront step.
Migration requires updating the model name while keeping the same API surface as GLM-4.6.
Hub snapshot: 2026-10-26 · HF API: 2026-10-26 07:20 UTC · Providers: 2026-10-26 07:26 UTC · Articles: 2026-10-26 07:27 UTC · Summary: 2026-10-07 15:09 UTC · Last verified 2026-10-26 07:27 UTC
