Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
50 vs 85
Hardware Fit
93 vs 64
Quality Score
31 vs 94

Hardware

qwen3.5:4b gemma-4-31b-it-mlx
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M4 Max
Cores1216
RAM8 GB128 GB
GPUIntegrated / UnknownApple M4 Max
OSUbuntu 26.04.1 LTSmacOS 26.5.2
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b gemma-4-31b-it-mlx
Tokens/sec92.613.6
First chunk323 ms16 ms
TTFT2.8 s558 ms
Load time9.0 s12.3 s
Memory usage2.9 GB0.0 GB
Memory %38%0%

HW Fit Score Breakdown

qwen3.5:4b

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

gemma-4-31b-it-mlx

Speed
14/50
TTFT
20/20
Memory
30/30

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

gemma-4-31b-it-mlx

Reasoning
19/20
Coding
19/20
Instruction
18/20
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 gemma-4-31b-it-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