Qwen3-Code Q4_K_XL full context @ 6 tokens/s
1x Nvidia 3090 (2020, $800)
1x Nvidia P40 (2017, $300)
2x EPYC Milan, 8 of 256 threads in use (2021, 2x$800)
DDR4 LRDIMM PC4-21300, 600 GB of 1TB in use ($1,250)
GIGABYTE MZ72-HB2 ($1,000)
`~/llama.cpp/build/bin/llama-cli --model /mnt/ollama/models/hf/Qwen3-Coder/UD-Q4_K_XL/Qwen3-Coder-480B-A35B-Instruct-UD-Q4_K_XL-00001-of-00006.gguf --threads 16 --ctx-size 262144 --n-gpu-layers 58 -ot "\.(6|7|8|9|[0-9][0-9]|[0-9][0-9][0-9])\.ffn_(gate|up|down)_exps.=CPU" --numa numactl -fa --cache-type-k q4_0 --cache-type-v q4_0`
ynniv
npub12a…x6fdh
2025-07-27 04:35:59 UTC
Author Public Key
npub12akj8hpakgzk6gygf9rzlm343nulpue3pgkx8jmvyeayh86cfrus4x6fdhPublished at
2025-07-27 04:35:59 UTCEvent JSON
{
"id": "25463a69f826f5b1190ddc42934dcbc2a23921c5b921d4670854d4255f08b8c8",
"pubkey": "576d23dc3db2056d208849462fee358cf9f0f3310a2c63cb6c267a4b9f5848f9",
"created_at": 1753590959,
"kind": 1,
"tags": [
[
"r",
"wss://nos.lol/"
],
[
"r",
"wss://nostr.land/"
],
[
"r",
"wss://nostr.wine/"
],
[
"r",
"wss://relay.damus.io/"
],
[
"r",
"wss://relay.getalby.com/v1"
],
[
"r",
"wss://relay.primal.net/"
],
[
"r",
"wss://theforest.nostr1.com/"
],
[
"r",
"wss://relay.snort.social/"
]
],
"content": "Qwen3-Code Q4_K_XL full context @ 6 tokens/s\n\n1x Nvidia 3090 (2020, $800)\n1x Nvidia P40 (2017, $300)\n2x EPYC Milan, 8 of 256 threads in use (2021, 2x$800)\nDDR4 LRDIMM PC4-21300, 600 GB of 1TB in use ($1,250)\nGIGABYTE MZ72-HB2 ($1,000)\n\n`~/llama.cpp/build/bin/llama-cli --model /mnt/ollama/models/hf/Qwen3-Coder/UD-Q4_K_XL/Qwen3-Coder-480B-A35B-Instruct-UD-Q4_K_XL-00001-of-00006.gguf --threads 16 --ctx-size 262144 --n-gpu-layers 58 -ot \"\\.(6|7|8|9|[0-9][0-9]|[0-9][0-9][0-9])\\.ffn_(gate|up|down)_exps.=CPU\" --numa numactl -fa --cache-type-k q4_0 --cache-type-v q4_0`\n\n",
"sig": "b840c2b964021a6af58f77538a0fe9d8b7dd7c7916b2a0b9eb0b8ea617b7d00ae86aee136778c195792d932ee4b8abd9f93c4d5f5ab7341ca18693c6c0a93023"
}