Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Excellent

Jul 4, 2026 · Apple M2 Pro

Global Score
50 vs 89
Hardware Fit
93 vs 88
Quality Score
31 vs 89

Hardware

qwen3.5:4b gemma4:12b
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M2 Pro
Cores1210
RAM8 GB16 GB
GPUIntegrated / UnknownApple M2 Pro
OSUbuntu 26.04.1 LTSmacOS 26.5
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b gemma4:12b
Tokens/sec92.618.4
First chunk323 ms758 ms
TTFT2.8 s758 ms
Load time9.0 s0.3 s
Memory usage2.9 GB7.5 GB
Memory %38%47%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
15/20
Memory
28/30

gemma4:12b

Speed
42/50
TTFT
20/20
Memory
26/30

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
12/15
Multilingual
0/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

gemma4:12b

Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b details | View gemma4:12b 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