Related changes
Jump to navigation
Jump to search
Enter a page name to see changes on pages linked to or from that page. (To see members of a category, enter Category:Name of category). Changes to pages on your Watchlist are in bold.
List of abbreviations:
- N
- This edit created a new page (also see list of new pages)
- m
- This is a minor edit
- b
- This edit was performed by a bot
- (±123)
- The page size changed by this number of bytes
27 August 2026
|
|
N 09:19 | Using Bonsai QWEN Models 2 changes history +2,284 [PeterHarding (2×)] | |||
|
|
09:19 (cur | prev) +23 PeterHarding talk contribs | ||||
| N |
|
09:18 (cur | prev) +2,261 PeterHarding talk contribs Created page with " See - https://www.youtube.com/watch?v=V6LmF7TuBmY (Bonsai 27B Runs Qwen 3.6 27B at 10x less memory) Not a corrupt download — a format mismatch. Q2_0 in that filename isn't stock llama.cpp's quant; it's Q2_0_g128, PrismML's custom ternary packing (2-bit slots, one FP16 scale per 128 weights) that only their fork's kernels understand. Your stock build computes a different byte size for the ternary tensors, so its running offset drifts from what's written in the header,..." | |||