Back to leaderboard

Gemma4-26B:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
92 vs 82
Hardware Fit
100 vs 71
Quality Score
89 vs 87

Hardware

Gemma4-26B:26b qwen3-coder:30b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLHP HP Pavilion Laptop 15-eh1xxx
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD Ryzen 5 5500U
Cores2012
RAM55 GB63 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUAMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 10 Enterprise LTSC 10.0.19044
Archarm64x64
Power Modebalancedbalanced

Performance

Gemma4-26B:26b qwen3-coder:30b
Tokens/sec61.314.3
First chunk185 ms869 ms
TTFT185 ms869 ms
Load time22.9 s0.3 s
Memory usage16.4 GB20.5 GB
Memory %30%32%

HW Fit Score Breakdown

Gemma4-26B:26b

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

qwen3-coder:30b

Speed
22/50
TTFT
20/20
Memory
29/30

Quality

Gemma4-26B:26b

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-coder:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View Gemma4-26B:26b details | View qwen3-coder:30b 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