Menu

← Leaderboard

Hermes-4.3-36B with Hermes Agent

Q6_K (GGUF) on llama.cpp commit a37cc46. Tested

Task completion
70% (21/30)
Tool-call success
53.4%
Decode tok/s
7.1
Prefill tok/s
558.3
Server memory
43.5 GB
Avg turns
3.4

Setup

Model
Hermes-4.3-36B
Family / maker
Hermes · Nous Research
Parameters
36B
Architecture
dense
Weights
NousResearch/Hermes-4.3-36B-GGUF
Quant
Q6_K (GGUF)
Engine
llama.cpp commit a37cc46
Hermes Agent
v0.22.4
Tested
2026-10-22
Context
64K (65,536 tokens); long-context task t09 at 128K or 192K
Memory tier
≤128 GB (measured)

Per-task results

  • t01: 3/3
  • t02: 3/3
  • t03: 3/3
  • t04: 3/3
  • t05: 2/3
  • t06: 2/3
  • t07: 2/3
  • t08: 0/3
  • t09: 0/3 (rerun 2026-10-23, 192K context)
  • t10: 3/3

Copy-paste config

1. Start the model server (llama.cpp)

Exact command used in our test. Download the GGUF from NousResearch/Hermes-4.3-36B-GGUF into ./models/.

llama-server --model ./models/hermes-4_3_36b-Q6_K.gguf --alias hermes-4-3-36b --host 127.0.0.1 --port 18080 --ctx-size 65536 --parallel 1 --n-gpu-layers 999 --flash-attn on --jinja

2. Point Hermes Agent at it

hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:18080/v1
hermes config set model.default hermes-4-3-36b

Other Hermes setups