Expired50% confidenceFactExact time
Through targeted two-bit compression techniques, the Gemma 4 E-to-B model's memory footprint has been compressed to approximately 1GB
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
OpenAI Confirms System Bug Caused Wrongful Account Suspensions; Multiple AI Tools Release Dense Updates
bilibili橘鸦Juya6/6/2026
Related Claims
Unverified模型量化技术将 Gemma 2B 的内存占用从约 5GB 降至 1.5GB 左右81% similarUnverifiedAfter Gemma 4 QAT optimization, the minimum memory footprint can be reduced to 1GB79% similarVerified4-bit quantization compresses each parameter to 0.5 bytes, theoretically compressing 140GB down to approximately 35–40GB.75% similarVerified4-bit quantization (such as Q4_K_M) can typically compress the memory footprint of a 3B model from approximately 6GB to approximately 2GB, with a precision loss of less than 2–3%.75% similarPartially VerifiedA standard FP32 model occupies 4 bytes per parameter, while INT4 quantization compresses this to 0.5 bytes, theoretically achieving an 8x memory saving.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/53680API
curl https://kongchang.com/api/v1/knowledge/claims/53680MCP
get_claim(id=53680)