nous-hermes2:latest
OLLAMA GGUFllama · 11B · Q4_0
Mar 1, 2026 · Apple M4
mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
68 vs 45
Hardware Fit
87 vs 100
Quality Score
60 vs 21
Hardware
nous-hermes2:latest mlx-community/quan…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
nous-hermes2:latest mlx-community/quan…
Tokens/sec15.944.4
First chunkN/A336 ms
TTFT345 ms336 ms
Load time0.4 sN/A
Memory usage6.6 GB0.1 GB
Memory %21%0%
HW Fit Score Breakdown
nous-hermes2:latest
Speed
27/50
TTFT
30/20
Memory
30/30
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
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
mlx-community/quantized…
Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak 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