Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

gemma4:e2b-mlx

OLLAMA GGUF
Not Rec.

Aug 26, 2026 · Apple M1 Pro

Global Score
29 vs 88
Hardware Fit
86 vs 79
Quality Score
4 vs 92

Hardware

qwen3:4b gemma4:e2b-mlx
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M1 Pro
Cores610
RAM7 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 22.04.5 LTSmacOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3:4b gemma4:e2b-mlx
Tokens/sec17.972.8
First chunk1010 ms134 ms
TTFT6.4 s30.0 s
Load time9.5 s2.6 s
Memory usage3.0 GB5.7 GB
Memory %40%36%

HW Fit Score Breakdown

qwen3:4b

Speed
50/50
TTFT
8/20
Memory
28/30

gemma4:e2b-mlx

Speed
50/50
TTFT
0/20
Memory
29/30

Quality

qwen3:4b

Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

gemma4:e2b-mlx

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:4b details | View gemma4:e2b-mlx 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