Unverified50% confidenceBenchmarkExact time
gemma4:12B-mlx is able to find code issues, but inference speed is relatively slow.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/9/2026
First Seen
Valid until: 11/7/2026
Sources
M4 MacBook 24GB本地大模型选型实战：9B到27B实测对比
Related Claims
UnverifiedMuse Glimmer 30B scored 51.2 on the SWE benchmark, meaning it can solve approximately half of real-world software engineering problems.60% similarUnverifiedMuse-Glimmer-30B在智能体工作流得90.87分、指令遵循90.86分、工具/CLI 88.84分，三项均优于Corpus 3.6 27B57% similarUnverifiedgemma-4-26b-a4b 模型名称中的 'a4b' 表示该模型采用了混合专家（MoE）架构，激活参数量约为4B56% similarUnverified在本地推理速度对比中，Agent A1（95 tokens/秒）快于Gemma 4 Coder和Qwen系列55% similarUnverifiedDeveloper Ivan tested version MTP-LX 0.3.5 and achieved a 93.3% accuracy rate on a math benchmark within 5 minutes and 30 seconds.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/712806API
curl https://kongchang.com/api/v1/knowledge/claims/712806MCP
get_claim(id=712806)