Unverified50% confidenceFactExact time
The full version of Neural 3 is only 29 MB, the smallest usable version is approximately 8 MB, and the weights are compressed to approximately 2 bits each.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedQ3_K_M compresses each weight to approximately 3 bits, reducing the weight size of a 27B model to approximately 12–13 GB.74% similarVerifiedEven compressing the weights to 214GB using 4-bit quantization still far exceeds the capacity of a single 48GB GPU.73% similarUnverifiedThe original QW3.6 27B model file size is approximately 54 GB; Prismo compresses it to under 4 GB through mathematical compression techniques, a compression ratio of more than 13×, and claims this does not affect model performance.73% similarUnverifiedUnder hardware conditions of 16 GB of memory, only models within 5 GB can be accommodated, so the developer used the Qwen 2.5 7B 4-bit quantized model, which is approximately 4.8 GB in size, with an 8K context window.72% similarUnverifiedUnsloth推出的1-bit量化版本将27B参数级别的模型压缩至仅6-8GB72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977847API
curl https://kongchang.com/api/v1/knowledge/claims/977847MCP
get_claim(id=977847)