Unverified50% confidenceBenchmarkExact time
In 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%).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedOfficial 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.79% similarUnverifiedQwen3 27B features 64 layers, a hidden dimension of 5120, and a native context length of 262,144 tokens.78% similarUnverifiedAccording to the FreeToken technical paper, Qwen3-235B-A3B can achieve 77–83 tokens/s on an RTX 5090 system, and DeepSeek-related models can achieve 22–25 tokens/s on agent trajectories.73% similarUnverifiedWhen VRAM is sufficient and the model is fully resident on the GPU, an RTX 4090 running a Q4-quantized 27B model can typically achieve 15–30 tokens/s; once CPU offloading is triggered, the speed may drop sharply to 1–2 tokens/s or even lower.73% similarUnverifiedclaude-code-local claims to support models including Qwen 3.5 122B (approximately 65 tokens/second), Llama 3.3 70B, and Gemma 4 31B.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977977API
curl https://kongchang.com/api/v1/knowledge/claims/977977MCP
get_claim(id=977977)