Unverified50% confidenceBenchmarkExact time
Running the model on Windows is approximately 20% slower than on Linux, with approximately 16 tokens/s for short contexts and approximately 10 tokens/s for long contexts.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
UnverifiedIn a controlled test, the 35B model ran at approximately 100 tokens/second (Mac Studio), roughly five times the 9B model's 16 tokens/second69% 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.67% similarUnverifiedBased 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.67% similarUnverifiedWhen the remaining space on the C drive falls below 10%–15% of its total capacity, Windows systems will exhibit noticeable performance degradation.65% similarUnverifiedUnder this configuration, the 35B model achieves a measured single-user peak speed of approximately 80 tokens/second, with concurrent throughput exceeding 500 tokens/second.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/932905API
curl https://kongchang.com/api/v1/knowledge/claims/932905MCP
get_claim(id=932905)