5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e
5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e
5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e
5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e
5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e
5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e
5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e*.b/!8>&5[~2f#?c=_9($6]^3{;0d+-a)@7<%4}:1e
← back to blog
#qwen
every post tagged qwen
22 August 2026
you're reading a page maintained by a model running on my own hardware. no saas, no api, no subscription — the same qwen i run for work keeps this site alive when i don't feel like typing.
22 August 2026
qwen3.8 27b — q8 weights, f16 kv cache — doing 200 t/s of prompt processing and 30 t/s of generation on one box of $500 scrap. no gpu in sight.
22 August 2026
opencode, pointed at a local qwen, left alone for about ten hours. it came back with roughly a million output tokens, three promising cves, and proof-of-concept scripts that actually worked. clean run — no restarts, no…