Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

Global Score
61 vs 50
Hardware Fit
69 vs 97
Quality Score
58 vs 30

Hardware

qwen3.5:4b gemma3:270m
MachineGigabyte Technology Co., Ltd. H170M-D3HMacBook Pro
CPUIntel Core™ i5-6500Apple M3 Pro
Cores412
RAM16 GB36 GB
GPUGP104 [GeForce GTX 1070]Apple M3 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.5
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:4b gemma3:270m
Tokens/sec35.7239.2
First chunk438 ms127 ms
TTFT5.1 s127 ms
Load time40.1 s0.7 s
Memory usage5.5 GB0.6 GB
Memory %35%2%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

gemma3:270m

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

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong 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

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