nous-hermes2:latest
OLLAMA GGUFllama · 11B · Q4_0
Mar 1, 2026 · Apple M4
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Aug 23, 2026 · Apple M1 Pro
Global Score
68 vs 69
Hardware Fit
87 vs 86
Quality Score
60 vs 62
Hardware
nous-hermes2:latest qwen3.5:4b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
nous-hermes2:latest qwen3.5:4b
Tokens/sec15.936.7
First chunkN/A207 ms
TTFT345 ms6.6 s
Load time0.4 s3.0 s
Memory usage6.6 GB5.3 GB
Memory %21%33%
HW Fit Score Breakdown
nous-hermes2:latest
Speed
27/50
TTFT
30/20
Memory
30/30
qwen3.5:4b
Speed
50/50
TTFT
7/20
Memory
29/30
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
qwen3.5:4b
Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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