Nanbeige4.3-33B claims to beat Qwen3.8-27B. on Hermes Agent tool calls on one 5090 it…
This is a dev post classified by AGK Intelligence as Other (an opinion), kept by the Dev Radar because it carries real work, not commentary.
Nanbeige4.3-33B claims to beat Qwen3.8-27B. on Hermes Agent tool calls on one 5090 it ties 82 vs 81, with 800 vs 799 on one-step calls, but finishes 25 of 30 real Hermes Agent tasks to Qwen's 29. tested: Nanbeige's 4-bit file (20.8 GB) against our Qwen3.8-27B rows on the same tests, one RTX 5090, llama.cpp. TL;DR: - tool calls over several turns: 82 vs 81 of 100, a tie - one-step tool calls: 800 vs 799 of 906, a tie - 30 Hermes Agent tasks at 64k context: 25 vs 29. Nanbeige only fits 64k with a compressed (q8_0) KV cache, Qwen ran without one - GPQA Diamond, thinking on: 81.3 vs 79.3, a tie
Posted by witcheer (23.4k followers) 3 h ago · 25 likes · 1.6k views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: llm-bench-rig.
More dev work like this
- 想研究 A 股短线形态，可以看看这个开源小工具。 — @bkdgiffug
- 研究产业链，可以从下游需求反向寻找上游瓶颈。 — @bkdgiffug
- Tokenized stocks did $3.9B in volume on @solana in October. — @envio_indexer
- A quarter of all @Uniswap v4 pools on @ethereum use a hook. — @envio_indexer
- Remember to pair big feature announcements with a PR campaign — @tarasshyn
- Turn arXiv papers into a literature review in 3 clicks — @askalphaxiv
- Bittensor 24H Market Snapshot — @taodaily_io
- Trading on Arc is already live. — @arc
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.5k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 00:02 UTC. Full method.