Back to leaderboard

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score
50 vs 65
Hardware Fit
97 vs 96
Quality Score
30 vs 51

Hardware

gemma3:270m qwen3-4b-qwen3.6-p…
MachineMacBook ProMac Studio
CPUApple M3 ProApple M2 Max
Cores1212
RAM36 GB96 GB
GPUApple M3 ProApple M2 Max
OSmacOS 15.7.5macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma3:270m qwen3-4b-qwen3.6-p…
Tokens/sec239.299.6
First chunk127 ms18 ms
TTFT127 ms1.6 s
Load time0.7 s4.8 s
Memory usage0.6 GB0.3 GB
Memory %2%0%

HW Fit Score Breakdown

gemma3:270m

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

qwen3-4b-qwen3.6-plus-r…

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

Quality

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

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong
View gemma3:270m details | View qwen3-4b-qwen3.6-p… 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