Expired50% confidenceFactExact time
In the STM32 embedded development test, the locally deployed DS4 model had an average output speed of approximately 23 tokens/second, memory usage spiked to 110 GB during inference, and the peak speed reached 83.8 tokens/second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedUnder a 4×RTX 3090 SXM4 configuration, the quantized version of GLM-5.2 achieves a token generation speed of approximately 6.3–6.8 tokens/second and a prompt evaluation speed of approximately 10.6 tokens/second.75% similarUnverifiedA 3B model typically achieves an inference speed of 10–30 tokens/second on a modern CPU via llama.cpp.74% similarUnverifiedThrough pure CPU inference and the 4-bit GGUF quantization format, llama.cpp enables a 7B-parameter model to achieve a generation speed of 20–40 tokens per second on an ordinary server without a GPU.73% similarUnverifieddecode阶段的生成速度近似等于内存带宽÷模型大小，例如在内存带宽273GB/s的M4 Pro上运行4GB的Q4量化7B模型理论最大生成速度约68 tokens/s72% similarUnverifiedIn a controlled test, the 35B model ran at approximately 100 tokens/second (Mac Studio), roughly five times the 9B model's 16 tokens/second72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/52524API
curl https://kongchang.com/api/v1/knowledge/claims/52524MCP
get_claim(id=52524)