Unverified50% confidenceBenchmarkExact time

On the test machine, Qwen3-Next-80B reads a 1024-token prompt at 62 tok/s and writes at 24 tok/s without the draft enabled; Qwen3-Coder-Next, also 48.4GB, reads at 66 and writes at 22.

1

Sources

50%

Confidence

Short-term (~14 days)

Relevance

10/13/2026

First Seen

Valid until: 10/27/2026

Sources

Janas Engine Runs 48GB MoE Model on a 32GB Laptop at 37 tok/s, Beating llama.cpp

Related Entities

Qwen3-Next-80Bmodel Qwen3-Coder-Nextmodel Janasproduct

Related Claims

VerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.74% similar UnverifiedThe Q4_K_M/GGUF version of Qwen 27B decodes at approximately 10.7 tok/s on the same machine, roughly 1/3.8 of the MLX version.74% similar UnverifiedUnoptimized baseline token decoding speeds for running Qwen 3 (27B): RTX 5090 ~75, RTX 4090 ~46, RTX 3090 ~40, M5 Max 31.4, DGX Spark 12–17, Ryzen AI Max 11.5 tokens/s.73% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/1017038

API

curl https://kongchang.com/api/v1/knowledge/claims/1017038

MCP

get_claim(id=1017038)