Back to leaderboard

qwen3.5:latest

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Not Rec.

Mar 8, 2026 · Apple M4

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

Global Score
34 vs 50
Hardware Fit
58 vs 97
Quality Score
23 vs 30

Hardware

qwen3.5:latest gemma3:270m
MachineMac miniMacBook Pro
CPUApple M4Apple M3 Pro
Cores1012
RAM16 GB36 GB
GPUApple M4Apple M3 Pro
OSmacOS 26.3macOS 15.7.5
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:latest gemma3:270m
Tokens/sec13.3239.2
First chunk438 ms127 ms
TTFT19.8 s127 ms
Load time0.2 s0.7 s
Memory usage8.0 GB0.6 GB
Memory %50%2%

HW Fit Score Breakdown

qwen3.5:latest

Speed
32/50
TTFT
1/20
Memory
25/30

gemma3:270m

Speed
50/50
TTFT
20/20
Memory
27/30

Quality

qwen3.5:latest

Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

gemma3:270m

Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
View qwen3.5:latest details | View gemma3:270m 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