Back to leaderboard

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

gemma3:1b

OLLAMA GGUF

gemma3 · 999.89M · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

Global Score
75 vs 57
Hardware Fit
50 vs 100
Quality Score
86 vs 39

Hardware

qwen2.5:72b gemma3:1b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUCortex-X925Cortex-A78AE
Cores206
RAM122 GB7 GB
GPUDevice 2e12Integrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen2.5:72b gemma3:1b
Tokens/sec4.433.7
First chunk529 ms2039 ms
TTFT529 ms2.0 s
Load time49.7 s7.3 s
Memory usage54.0 GB0.8 GB
Memory %44%11%

HW Fit Score Breakdown

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

gemma3:1b

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

Quality

qwen2.5:72b

Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

gemma3:1b

Reasoning
6/20
Coding
3/20
Instruction
14/20
Structured
8/15
Math
1/15
Multilingual
7/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
View qwen2.5:72b details | View gemma3:1b 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