Unverified50% confidenceFactExact time
Kobold cannot load larger models; Qwen 35B (approximately 20.6 GB) and GLM 31B (approximately 17.7 GB) require the LLAMA backend.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedThe BF16 weights of the 27B model are approximately 54GB (27B × 2 bytes).70% similarUnverifiedThe UP host advises that individual users are not recommended to deploy Qwen3.8-27B, and those with less than 32GB of memory should give up entirely, because the Q4 version occupies approximately 36GB of memory.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999480API
curl https://kongchang.com/api/v1/knowledge/claims/999480MCP
get_claim(id=999480)