Back to leaderboard

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

qwen2.5-coder-0.5b-instruct

LM-STUDIO GGUF

qwen2 · 0.5B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
76 vs 55
Hardware Fit
92 vs 89
Quality Score
69 vs 40

Hardware

gemma3:4b qwen2.5-coder-0.5b…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperLENOVO 20BUS00700
CPUCortex-A78AEIntel Core™ i5-5300U
Cores64
RAM7 GB16 GB
GPUIntegrated / UnknownIntel(R) HD Graphics 5500
OSUbuntu 22.04.5 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

gemma3:4b qwen2.5-coder-0.5b…
Tokens/sec15.013.5
First chunk2380 ms1292 ms
TTFT2.4 s1.3 s
Load time13.6 sN/A
Memory usage2.6 GB0.4 GB
Memory %35%2%

HW Fit Score Breakdown

gemma3:4b

Speed
45/50
TTFT
18/20
Memory
29/30

qwen2.5-coder-0.5b-inst…

Speed
41/50
TTFT
20/20
Memory
28/30

Quality

gemma3:4b

Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen2.5-coder-0.5b-inst…

Reasoning
7/20
Coding
7/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
4/10
Reasoning: Weak Coding: Weak 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