Unverified50% confidenceFactExact time
In Sportello chiaro's tests, the Gemma 3 1B (Q4_K_M) model run via llama-cpp-python was used.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedIn the demo, when querying a simple factual question the router selects the Qwen3.5 4-billion-parameter small model, while complex tasks are handled by the Gemma model at a speed of approximately 93.1 tokens per second.59% similarUnverifiedQwen3 8B版本在工具调用（Function Calling）基准测试中表现突出58% similarUnverifiedOn the BFCL tool-calling test, SmolLM3-3B scores 0.945, slightly above Gemma 4 E2B's 0.927, but the difference is not significant; Qwen3-4B (0.940), Qwen3-1.7B (0.935), Qwen2.5-1.5B (0.910), and Granite 3.3 2B (0.920) are all at the same level as Gemma.58% similarUnverifiedThe test was conducted based on the Qwen3 27B NVFP4 quantized version released by Unsloth.58% similarUnverifiedThis test is a single-source personal test; the model designation is labeled as Qwen 3.8 27B with naming ambiguity, and details such as the actual configuration, quantization method, and generation time have not been disclosed, leaving reproducibility to be verified.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033450API
curl https://kongchang.com/api/v1/knowledge/claims/1033450MCP
get_claim(id=1033450)