Expired60% confidenceBenchmarkExact time
During the prefill phase, Ornith's speed approached 200 tokens per second, approximately 20 tokens faster than Qwen.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
Valid until: 10/7/2026(expired)
Sources
16GB VRAM Showdown: Ornith 35B vs Qwen 35B — Full Benchmark Comparison
bilibili程序员-智能译站7/7/2026
Related Claims
UnverifiedQwen 3.6 achieved a prefill speed of 400 tokens/second and a generation speed of close to 40 tokens/second during testing.72% similarUnverifiedIn decode speed tests, speeds of approximately 45 tokens/second are achievable within 20,000 tokens, dropping sharply to approximately 20 tokens/second beyond 30,000 tokens.63% similarUnverifiedAfter enabling MTP, inference speed fluctuates significantly, sometimes exceeding 40 tokens/second and sometimes dropping to 25 tokens/second.62% similarUnverifiedThe generation speed of a local 7B model is typically 20–50 tokens per second, whereas cloud-based APIs can reach 100+ tokens per second62% similarUnverifiedIt is generally considered that single-concurrency output above 100 tokens/second is sufficient to achieve a smooth typewriter effect, and at approximately 200 tokens/second, generating a 2,000-character long text takes only about 10 seconds.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/342891API
curl https://kongchang.com/api/v1/knowledge/claims/342891MCP
get_claim(id=342891)