nous-hermes2:latest
OLLAMA GGUFllama · 11B · Q4_0
Mar 1, 2026 · Apple M4
qwen3.5:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Mar 10, 2026 · Apple M4
Global Score
68 vs 66
Hardware Fit
87 vs 34
Quality Score
60 vs 80
Hardware
nous-hermes2:latest qwen3.5:27b
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 qwen3.5:27b
Tokens/sec15.94.0
First chunkN/A1655 ms
TTFT345 ms1.7 s
Load time0.4 s12.9 s
Memory usage6.6 GB21.3 GB
Memory %21%89%
HW Fit Score Breakdown
nous-hermes2:latest
Speed
27/50
TTFT
30/20
Memory
30/30
qwen3.5:27b
Speed
8/50
TTFT
20/20
Memory
6/30
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
qwen3.5:27b
Reasoning
16/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong
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