Expired50% confidenceBenchmarkExact time
In a controlled test, the 35B model ran at approximately 100 tokens/second (Mac Studio), roughly five times the 9B model's 16 tokens/second
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/13/2026
First Seen
Valid until: 10/11/2026(expired)
Sources
Ornith 1.0 九B模型本地实测：塔防游戏暴露小模型编程瓶颈
Related Claims
UnverifiedBased on the MLX framework, top-configured Mac models can achieve a generation speed of approximately 20 tokens/second when running the Llama-3-70B quantized model.81% similarUnverifiedUnder 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.74% similarUnverifiedIn 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.72% similarUnverifiedThe 4-bit quantized GGUF format version of llama.cpp enables the Llama 3.1 70B model to run on an Apple M2 Ultra with 64GB unified memory at an inference speed of approximately 20–30 tokens/second.71% similarUnverifiedSmall models (1B–7B parameters) used for text completion tasks can run smoothly on Macs with 8 GB or more of unified memory, with inference latency kept within a few hundred milliseconds.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/502659API
curl https://kongchang.com/api/v1/knowledge/claims/502659MCP
get_claim(id=502659)