Unverified50% confidenceReleaseExact time
Bonsai 2, released by PrismML, is a heavily quantized version based on Qwen 3.8 27B.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
UnverifiedBonsai is based on Qwen 3's full-size 27B model72% similarUnverifiedBonsai 2 uses the PQ2_0 ternary quantization format, with a model size of 7.2GB.68% similarUnverifiedPrismML compressed Qwen 3.6 from the original approximately 54 GB to under 4 GB, a compression ratio exceeding 13×.66% similarUnverifiedQwen3.8-Max-0902 uses a Mixture-of-Experts (MoE) architecture with 2.4T parameters and supports a context length of 128K.64% similarUnverifiedQwen 3.5 9B (Q6_K) output at approximately 168 tok/s, faster than Bonsai 2 27B's 101 tok/s.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/933010API
curl https://kongchang.com/api/v1/knowledge/claims/933010MCP
get_claim(id=933010)