Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

nous-hermes2:latest

OLLAMA GGUF

llama · 11B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
53 vs 68
Hardware Fit
82 vs 87
Quality Score
41 vs 60

Hardware

qwen3.5:4b-mlx nous-hermes2:latest
MachineMac miniMacBook Air
CPUApple M2Apple M4
Cores810
RAM8 GB32 GB
GPUApple M2Apple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx nous-hermes2:latest
Tokens/sec24.715.9
First chunk302 msN/A
TTFT7.4 s345 ms
Load time3.2 s0.4 s
Memory usage3.8 GB6.6 GB
Memory %47%21%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

nous-hermes2:latest

Speed
27/50
TTFT
30/20
Memory
30/30

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

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

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest