Unverified50% confidenceFactExact time
When running a 35B-parameter model on an 80GB H100 for conversation, each generated token actually uses only about 3B equivalent of weights.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe developer uses the Qwen3.6-35B-A3B model: it has 35B weights in total, uses only 3B weights when processing each word, has a computational cost comparable to ordinary 4B and 8B models, and runs on their own gateway (vLLM).70% similarUnverifiedThe 35B-A3B mixture-of-experts model has 35B total parameters, with approximately 3 billion parameters actually activated per inference, making it suitable for running on GPUs with 16 GB of VRAM.70% similarUnverifiedWith 64 GB of memory, models with 30B to 34B parameters can run smoothly under Q4 quantization, while a 70B model is barely feasible under Q4 but with a noticeably slower response speed.69% similarUnverifiedThe 35B model can achieve 45 to 60 tokens per second on a 4090-class GPU.69% similarUnverified原本需要 A100 80GB 才能完成的 70B 参数模型微调任务，在 Unsloth 优化下可以在消费级 RTX 4090（24GB）上运行68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013079API
curl https://kongchang.com/api/v1/knowledge/claims/1013079MCP
get_claim(id=1013079)