Unverified50% confidenceBenchmarkExact time
SponsorPulse uses local Gemma 3:1b running via Ollama, reaching speeds of 120+ tokens per second on Apple Silicon.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedOllama 0.19 was released on March 30 and switched to the MLX backend on Apple Silicon, with decoding speed jumping from 58 tokens/s to 112.64% similarUnverifiedAccording to Stridenote, Ollama tests showed that Qwen3.5 35b's speed jumped from 58 token/s to 112 token/s after switching to Apple Silicon's MLX.63% similarUnverified运行Stable Diffusion + ControlNet生成艺术二维码建议使用8GB以上显存的GPU（如NVIDIA RTX 3060及以上），Apple Silicon可通过MPS后端运行但速度较慢62% similarUnverifiedGemma 3 1B has a memory footprint of less than 1 GB and requires only a few hundred milliseconds for inference, making it suitable for offline operation without consuming large amounts of power.62% similarUnverifiedOn an Apple Silicon M4 Pro (12 cores, ARM NEON), Falcon3 1B Instruct reaches 137.5 t/s prompt processing and 98.6 t/s generation speed, with 1.9 GB memory usage.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1039389API
curl https://kongchang.com/api/v1/knowledge/claims/1039389MCP
get_claim(id=1039389)