Back to leaderboard

qwen2-57b:57B

OLLAMA GGUF

qwen2moe · 57.4B · Q4_K_M

Good

Aug 18, 2026 · Intel Core™ Ultra X7 358H

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
67 vs 76
Hardware Fit
51 vs 92
Quality Score
74 vs 69

Hardware

qwen2-57b:57B gemma3:4b
MachineGMKtec NucBox EVO-T2SNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ Ultra X7 358HCortex-A78AE
Cores166
RAM64 GB7 GB
GPUIntel(R) Arc(TM) B390 GPUIntegrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2-57b:57B gemma3:4b
Tokens/sec8.615.0
First chunk1573 ms2380 ms
TTFT1.6 s2.4 s
Load time29.0 s13.6 s
Memory usage32.8 GB2.6 GB
Memory %52%35%

HW Fit Score Breakdown

qwen2-57b:57B

Speed
10/50
TTFT
17/20
Memory
24/30

gemma3:4b

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

Quality

qwen2-57b:57B

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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