Expired50% confidenceBenchmarkExact time
The author tested on an M3 Max and found that at a context length of 32,000 tokens, Dwarf Star generates 26.7 tokens per second (author's own test data, not third-party benchmarks).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/25/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/23/2026(expired)
Sources
Redis之父如何将2840亿参数DeepSeek塞进普通笔记本
Related Claims
UnverifiedMiniMax M3 每个 token 推理时约激活 23B 参数69% similarUnverifiedThe ratio of activated parameters to total parameters for MiniMax M3, 23B/428B, is approximately 5.4%.66% similarUnverified在覆盖九大维度共403道题的测试中，Muse-Glimmer-30B综合均分为76.04，比Corpus 3.6 27B的75.57高出0.47分65% similarUnverifiedMuse Glimmer 30B is reported to achieve 74.9 tokens per second on an RTX 5090, and reviewers observed approximately 60–65 tokens/sec running the full-precision version on an RTX 3090.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/613178API
curl https://kongchang.com/api/v1/knowledge/claims/613178MCP
get_claim(id=613178)