Menu

← Leaderboard

Gemma 4 26B-A4B with Hermes Agent

Q8_0 (GGUF) on llama.cpp commit a37cc46. Tested

Task completion
100% (30/30)
Tool-call success
61.9%
Decode tok/s
46.5
Prefill tok/s
2637.1
Server memory
26.9 GB
Avg turns
5.2

Setup

Model
Gemma 4 26B-A4B
Family / maker
Gemma · Google
Parameters
26B (4B active)
Architecture
MoE
Weights
ggml-org/gemma-4-26B-A4B-it-GGUF
Quant
Q8_0 (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: 3/3
  • t06: 3/3
  • t07: 3/3
  • t08: 3/3
  • t09: 3/3 (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 ggml-org/gemma-4-26B-A4B-it-GGUF into ./models/.

llama-server --model ./models/gemma-4-26B-A4B-it-Q8_0.gguf --alias gemma-4-26b-a4b --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 gemma-4-26b-a4b

Other Gemma setups