Back to leaderboard

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

Global Score
46 vs 95
Hardware Fit
93 vs 94
Quality Score
26 vs 96

Hardware

gemma3:4b qwen3-30b-a3b-thin…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMac Studio
CPUCortex-A78AEApple M2 Max
Cores612
RAM7 GB96 GB
GPUIntegrated / UnknownApple M2 Max
OSUbuntu 22.04.5 LTSmacOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma3:4b qwen3-30b-a3b-thin…
Tokens/sec14.980.4
First chunk2204 ms46 ms
TTFT2.2 s1.8 s
Load time2.0 sN/A
Memory usage2.6 GB21.2 GB
Memory %35%22%

HW Fit Score Breakdown

gemma3:4b

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

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

Quality

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

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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