Back to leaderboard

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

Global Score
68 vs 46
Hardware Fit
59 vs 93
Quality Score
72 vs 26

Hardware

qwen2.5-coder:7b gemma3:4b
MachineASUSNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Gen Intel® Core™ i7-13700KCortex-A78AE
Cores246
RAM64 GB7 GB
GPUNVIDIA GeForce RTX 3070Integrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modeunknownbalanced

Performance

qwen2.5-coder:7b gemma3:4b
Tokens/sec34.414.9
First chunk1991 ms2204 ms
TTFT2.0 s2.2 s
Load time40.6 s2.0 s
Memory usage5.0 GB2.6 GB
Memory %8%35%

HW Fit Score Breakdown

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

gemma3:4b

Speed
45/50
TTFT
19/20
Memory
29/30

Quality

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

gemma3:4b

Reasoning
11/20
Coding
11/20
Instruction
0/20
Structured
0/15
Math
4/15
Multilingual
0/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor

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