Unverified50% confidenceBenchmarkExact time
On 8×B200, DiffusionGemma 26B MoE + ORL reaches 7,708 tokens/s at NVFP4 precision (single-request decoding).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedA single RTX 5090 with LLaDA-2.1-mini + ORL reaches 2,788 tokens/s at NVFP4 precision (single-request decoding, batch size 1).79% 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.68% similarUnverifiedd1-omni-600M 基于 LFM2.5-Encoder-350M 双向编码器构建，而非在因果解码器上接分类头，上下文窗口为 16,384 tokens。65% 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.65% similarUnverifiedIn benchmark testing on an AMD RX 7900 GPU, Ornith 35B achieved an overall accuracy of 85% (18 out of 21 passed), a generation speed of 74 tokens/s, a prompt processing speed of 850 tokens/s, and a VRAM usage of 20 GB.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049950API
curl https://kongchang.com/api/v1/knowledge/claims/1049950MCP
get_claim(id=1049950)