Back to leaderboard

google/gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_0

Excellent

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Qwen3-Coder-30B:30B

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

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

Global Score
82 vs 88
Hardware Fit
56 vs 91
Quality Score
93 vs 87

Hardware

google/gemma-4-26b… Qwen3-Coder-30B:30B
MachineDocker ContainerGMKtec NucBox EVO-T2S
CPUIntel Gen Intel® Core™ i9-11900HIntel Core™ Ultra X7 358H
Cores1616
RAM15 GB64 GB
GPUTigerLake-H GT1 [UHD Graphics]Intel(R) Arc(TM) B390 GPU
OSUbuntu 26.04 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

google/gemma-4-26b… Qwen3-Coder-30B:30B
Tokens/sec12.032.2
First chunk86 ms540 ms
TTFT2.8 s540 ms
Load time57.2 s15.6 s
Memory usage9.1 GB17.7 GB
Memory %59%28%

HW Fit Score Breakdown

google/gemma-4-26b-a4b-…

Speed
22/50
TTFT
14/20
Memory
20/30

Qwen3-Coder-30B:30B

Speed
41/50
TTFT
20/20
Memory
30/30

Quality

google/gemma-4-26b-a4b-…

Reasoning
17/20
Coding
19/20
Instruction
20/20
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: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

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