Unverified50% confidenceFactExact time
If the GPU does not support 16-bit shaders, Go Outside will automatically switch to the q4f32 build of the same model; on mobile there is a lighter option using approximately 600MB Gemma 3 1B (gemma3-1b-it-q4f16_1-MLC).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedMiniCPM和Qwen-0.5B等1B以下轻量模型配合INT4量化可以在手机芯片上运行67% similarVerifiedThe Qwen2.5 9B model can run smoothly on consumer-grade GPUs (such as those with 8GB of VRAM).65% similarUnverifiedA single 32GB VRAM GPU cannot fully accommodate a 70B Q4 quantized model and requires GPU+CPU hybrid inference with llama.cpp.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001763API
curl https://kongchang.com/api/v1/knowledge/claims/1001763MCP
get_claim(id=1001763)