Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
53 vs 81
Hardware Fit
82 vs 100
Quality Score
41 vs 73

Hardware

qwen3.5:4b-mlx gemma3n:latest
MachineMac miniSupermicro AS -2015HS-TNR
CPUApple M2AMD EPYC 9654P 96-Core Processor
Cores864
RAM8 GB128 GB
GPUApple M2GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 26.5.2Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5:4b-mlx gemma3n:latest
Tokens/sec24.7108.7
First chunk302 ms333 ms
TTFT7.4 s333 ms
Load time3.2 s4.5 s
Memory usage3.8 GB8.6 GB
Memory %47%7%

HW Fit Score Breakdown

qwen3.5:4b-mlx

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

gemma3n:latest

Speed
50/50
TTFT
20/20
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

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:4b-mlx details | View gemma3n:latest details

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