Back to leaderboard

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
50 vs 37
Hardware Fit
97 vs 73
Quality Score
30 vs 22

Hardware

gemma3:270m deepseek-r1:1.5b
MachineMacBook ProLENOVO 20L7CTO1WW
CPUApple M3 ProIntel Core™ i5-8350U
Cores128
RAM36 GB23 GB
GPUApple M3 ProKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 15.7.5Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power

Performance

gemma3:270m deepseek-r1:1.5b
Tokens/sec239.218.4
First chunk127 ms593 ms
TTFT127 ms30.0 s
Load time0.7 s3.8 s
Memory usage0.6 GB1.0 GB
Memory %2%4%

HW Fit Score Breakdown

gemma3:270m

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

deepseek-r1:1.5b

Speed
43/50
TTFT
0/20
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

deepseek-r1:1.5b

Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak 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