Unverified50% confidenceFactExact time
The dense Qwen3.8-27B model's 3-bit version actually scored 0.05 higher (within noise range), but the number of tokens generated per task increased by 40% (confidence interval 1.25–1.59x).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedIn the 16-concurrency, 256-token-output test, Gemma 4 E2B achieves an output speed of 1887 tokens/second, and the models faster than it include Qwen2.5-0.5B (4176, 2.21x), Qwen3-0.6B (3210, 1.70x), Qwen2.5-1.5B (2780, 1.47x), and Qwen3-1.7B (2049, 1.09x).76% similarUnverifiedQwen 2.5 0.5B在WebGPU下达到37-40 tokens/s，中位回复耗时约1.8秒，是三个测试模型中最慢的。75% similarUnverifiedExperience internalization fine-tuning improved Qwen3-8B-27B's one-shot score from 37.07 to 48.22, while reducing generated tokens from 6.41 million to 570,000 (an 11-fold reduction).74% similarUnverifiedQwen3.8-Flash-Next's NVFP4 quantized version scored 0.50 and its 3-bit quantized version scored 0.48, both exceeding Claude Haiku 5.5's 0.47.74% similarUnverifiedIn a failure case using Qwen3 0.6B as the drafter for a 4B model with the speculative token count set to 4, throughput crashed from 58.2 tokens/s to 16 tokens/s, and from 700 to 240 at 16 concurrency.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1127042API
curl https://kongchang.com/api/v1/knowledge/claims/1127042MCP
get_claim(id=1127042)