Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

Global Score
81 vs 76
Hardware Fit
98 vs 46
Quality Score
74 vs 89

Hardware

qwen3.5:4b gemma4:31b
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M4 Max
Cores1216
RAM8 GB64 GB
GPUIntegrated / UnknownApple M4 Max
OSUbuntu 26.04.1 LTSmacOS 26.3.1
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b gemma4:31b
Tokens/sec93.722.4
First chunk249 ms565 ms
TTFT249 ms30.0 s
Load time10.1 s6.9 s
Memory usage2.9 GB43.9 GB
Memory %38%69%

HW Fit Score Breakdown

qwen3.5:4b

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

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

Quality

qwen3.5:4b

Reasoning
15/20
Coding
13/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

gemma4:31b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b details | View gemma4:31b 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