Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

gemma4:e4b-it-q8_0

OLLAMA GGUF

gemma4 · 8.0B · Q8_0

Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
29 vs 88
Hardware Fit
86 vs 100
Quality Score
4 vs 83

Hardware

qwen3:4b gemma4:e4b-it-q8_0
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:e4b-it-q8_0
Tokens/sec17.927.8
First chunk1010 ms204 ms
TTFT6.4 s204 ms
Load time9.5 s6.6 s
Memory usage3.0 GB5.0 GB
Memory %40%31%

HW Fit Score Breakdown

qwen3:4b

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

gemma4:e4b-it-q8_0

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

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:e4b-it-q8_0

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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