Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
84 vs 76
Hardware Fit
66 vs 92
Quality Score
92 vs 69

Hardware

qwen3.8:27b gemma3:4b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUCortex-X925Cortex-A78AE
Cores206
RAM122 GB7 GB
GPUDevice 2e12Integrated / Unknown
OSUbuntu 24.04.5 LTSUbuntu 22.04.5 LTS
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen3.8:27b gemma3:4b
Tokens/sec29.415.0
First chunk306 ms2380 ms
TTFT4.8 s2.4 s
Load time5.3 s13.6 s
Memory usage16.2 GB2.6 GB
Memory %13%35%

HW Fit Score Breakdown

qwen3.8:27b

Speed
31/50
TTFT
5/20
Memory
30/30

gemma3:4b

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

Quality

qwen3.8:27b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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