Unverified50% confidenceFactExact time
Google Gemma 4's 12B model has a file size of 7.7 to 8GB, and in testing it used 8.8GB of VRAM on a 12GB GPU, leaving about 3.4GB (default 4000 context).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedQwen 3.8's 27-billion-parameter model is approximately 15.3 GB after 4-bit quantization, but actual memory usage can surge to over 17 GB after a conversation of several thousand characters, meaning 16 GB of VRAM is insufficient and 24 GB is needed for comfortable use.75% similarVerifiedAfter quantization, EmbeddingGemma 2 requires only approximately 191 MB of active memory for text-only weights on the Google Pixel 11 Pro, while the full multimodal model requires approximately 567 MB.74% similarUnverifiedEmbedding Gemma 2 has 740 million parameters, consisting of a 270M text encoder, a 170M vision encoder, and a 300M audio encoder, with runtime dynamic memory of approximately 191MB to 567MB; the 270M version requires a minimum of 0.5GB memory to run, and the full multimodal version can run locally with 1GB of memory.74% similarVerifiedCalculated from a storage perspective: 27B parameters × 2 bytes (FP16) ≈ 54 GB, INT8 ≈ 27 GB, INT4 ≈ 13.5 GB, 2-bit ≈ 6.75 GB, 1.5-bit approaches 5 GB; fitting within 4 GB means the average bit width needs to be below 1.5-bit.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1056747API
curl https://kongchang.com/api/v1/knowledge/claims/1056747MCP
get_claim(id=1056747)