Unverified50% confidenceFactExact time
The test covered 8 local models: Qwen3's 0.6B, 1.7B, 4B, 8B, and 14B, as well as Gemma3's 1B, 4B, and 12B, all deployed via Ollama with thinking mode disabled.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe study tested four sizes of the Qwen3 series—0.6B, 1.7B, 4B, and 8B—running at FP16 precision, greedy decoding, a single frozen prompt, and no fine-tuning.80% similarUnverifiedThe nine checkpoints consist of four target models (Qwen3's 4B, 8B, 14B, and Gemma 4's 12B) multiplied by three algorithms79% similarUnverifiedQwen3 is available on Ollama in multiple sizes including 0.6B, 1.7B, 4B, and 8B77% similarUnverifiedIn actual tests of 8-bit and 4-bit (OQ4E) quantization of the same Qwen3 27B model based on the MLX framework, each won 5 out of 10 accuracy tests, resulting in a tie.73% similarUnverifiedQwen2.5-72B approaches the performance of Llama-3.1-405B across multiple benchmarks.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018316API
curl https://kongchang.com/api/v1/knowledge/claims/1018316MCP
get_claim(id=1018316)