Unverified50% confidenceSolutionExact time
If the 4-bit Gemma files still fail to start, you can fall back to using dtype: 'q8' (about 545 MB) as an alternative.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
VerifiedGemma 4的1B/2B模型量化后仅需4GB显存即可运行68% similarUnverifiedGemma 3 offers multiple sizes covering different hardware, including a minimum version of approximately 1GB, medium-sized versions, and large versions such as 12B and 27B.63% 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.63% similarUnverifiedGemma 4 E2B's KV cache capacity is 321,280 tokens, which is 2.6 to 6.3 times that of Granite 3.3 2B (125,184), SmolLM3-3B (120,320), Qwen3-1.7B (100,096), and Qwen3-4B (50,688).61% similarUnverifiedIf 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).61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1028553API
curl https://kongchang.com/api/v1/knowledge/claims/1028553MCP
get_claim(id=1028553)