Back to leaderboard

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 10, 2026 · Apple M4

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

Global Score
66 vs 76
Hardware Fit
34 vs 46
Quality Score
80 vs 89

Hardware

qwen3.5:27b gemma4:31b
MachineMac miniMacBook Pro
CPUApple M4Apple M4 Max
Cores1016
RAM24 GB64 GB
GPUApple M4Apple M4 Max
OSmacOS 26.3macOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:27b gemma4:31b
Tokens/sec4.022.4
First chunk1655 ms565 ms
TTFT1.7 s30.0 s
Load time12.9 s6.9 s
Memory usage21.3 GB43.9 GB
Memory %89%69%

HW Fit Score Breakdown

qwen3.5:27b

Speed
8/50
TTFT
20/20
Memory
6/30

gemma4:31b

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

Quality

qwen3.5:27b

Reasoning
16/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong 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 qwen3.5:27b 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