nous-hermes2:latest
OLLAMA GGUFllama · 11B · Q4_0
Mar 1, 2026 · Apple M4
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
Global Score
68 vs 33
Hardware Fit
87 vs 50
Quality Score
60 vs 25
Hardware
nous-hermes2:latest gemma4:26b
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
nous-hermes2:latest gemma4:26b
Tokens/sec15.920.0
First chunkN/A941 ms
TTFT345 ms30.0 s
Load time0.4 s0.2 s
Memory usage6.6 GB20.3 GB
Memory %21%85%
HW Fit Score Breakdown
nous-hermes2:latest
Speed
27/50
TTFT
30/20
Memory
30/30
gemma4:26b
Speed
42/50
TTFT
0/20
Memory
8/30
Quality
nous-hermes2:latest
Reasoning
11/20
Coding
9/20
Instruction
12/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma4:26b
Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest