Unverified50% confidenceBenchmarkExact time
Official 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
Unverifiedclaude-code-local claims to support models including Qwen 3.5 122B (approximately 65 tokens/second), Llama 3.3 70B, and Gemma 4 31B.75% similarUnverifiedThe context length of mainstream open-source multimodal models is typically between 4K and 32K tokens: LLaVA-1.5 is 4,096 tokens, Qwen-VL is 8,192 tokens, and InternVL2 extends to 32K.75% similarUnverifiedFor a typical 7B model (32 layers, 32 heads, 128 dimensions) processing a 2048-token sequence at FP16 precision with a batch size of 8, the KV Cache consumes approximately 4 GB of VRAM.75% 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% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924349API
curl https://kongchang.com/api/v1/knowledge/claims/924349MCP
get_claim(id=924349)