Back to leaderboard

gemma3:1b

OLLAMA GGUF

gemma3 · 999.89M · Q4_K_M

Good

Feb 28, 2026 · Apple M4

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
68 vs 78
Hardware Fit
98 vs 59
Quality Score
55 vs 86

Hardware

gemma3:1b qwen2.5-coder:32b
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modeunknownperformance

Performance

gemma3:1b qwen2.5-coder:32b
Tokens/sec39.49.5
First chunkN/A394 ms
TTFT362 ms395 ms
Load time0.3 s72.1 s
Memory usage1.3 GB26.5 GB
Memory %4%22%

HW Fit Score Breakdown

gemma3:1b

Speed
40/50
TTFT
30/20
Memory
28/30

qwen2.5-coder:32b

Speed
9/50
TTFT
20/20
Memory
30/30

Quality

gemma3:1b

Reasoning
6/20
Coding
13/20
Instruction
15/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

qwen2.5-coder:32b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma3:1b details | View qwen2.5-coder:32b 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