Expired50% confidenceBenchmarkExact time
1-bit Bonsai achieves an intelligence density score of 0.53/GB, which is more than 10 times that of the full-precision model and approximately 2.7 times that of the best low-bit alternatives
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/18/2026(expired)
Sources
Related Claims
Unverified8GB of VRAM can run 3B–7B quantized models, but inference speed is slow.66% similarPartially VerifiedFor the 4-bit quantized version of a 7B parameter model, at least 8GB of memory and a modern multi-core CPU are typically required for smooth operation, with inference speeds of approximately 10–30 tokens per second65% similarUnverified1.5 TB of unified memory means that hundred-billion-parameter-scale models can be run on a single machine at INT8 precision, or models approaching one trillion parameters at INT4 precision, without requiring multi-card model parallelism.64% similarUnverified8 GB of memory is the minimum configuration for running Stable Diffusion, and generation speed and resolution will be noticeably limited.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/569984API
curl https://kongchang.com/api/v1/knowledge/claims/569984MCP
get_claim(id=569984)