Unverified50% confidenceBenchmarkExact time
JetBrains self-reported data: Mellum2.1 reaches 7,969 tokens/s on a single H200, while Qwen3.5-9B reaches 4,347 tokens/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedIn a llama.cpp environment with Qwen3 27B, the R9700 achieved 27.1 tokens/s (approximately 65% of bandwidth ceiling) and the B70 achieved 21.4 tokens/s (just over approximately 50%).74% similarUnverifiedOfficial benchmark results show that the Qwen3.6 27B dense model with NVFP4 quantization achieves 202 token/s at single concurrency, 400 token/s at dual concurrency, and 1147 token/s at 8 concurrency.70% similarUnverifiedJordan Ilchif tested Qwen 3.8 27B on a 32GB M4 MacBook Air, with Ollama's NVFP4 build running at 17.2 tokens/s, pure MLX at 6.6 tokens/s, and LLAMA.cpp at 4.4 tokens/s, but the formats were different.70% similarUnverifiedRunning Gemma 4 26B on an M3 Max, MLX is 65.0 tokens/s and LLAMA.cpp is 63.9 tokens/s, essentially a tie between the two.70% similarUnverifiedIn a fair 4-bit comparison, MLX with D-Flash 2 speculative decoding ran at 16.6 tokens/s, versus Ollama Q4's 5.7 tokens/s.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016868API
curl https://kongchang.com/api/v1/knowledge/claims/1016868MCP
get_claim(id=1016868)