Back to leaderboard

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

LM-STUDIO GGUF

gemma4 · 26B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 24, 2026 · Intel Core™ Ultra X7 358H

Global Score
93 vs 82
Hardware Fit
96 vs 59
Quality Score
92 vs 92

Hardware

google/gemma-4-26b… Qwen3-80B:80B
MachineMicro-Star International Co., Ltd. MS-7E51GMKtec NucBox EVO-T2S
CPUAMD Ryzen 7 9700X 8-Core ProcessorIntel Core™ Ultra X7 358H
Cores1616
RAM31 GB64 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-26b… Qwen3-80B:80B
Tokens/sec109.719.6
First chunk29 ms823 ms
TTFT156 ms823 ms
Load timeN/A41.6 s
Memory usage14.6 GB46.9 GB
Memory %47%74%

HW Fit Score Breakdown

google/gemma-4-26b-a4b-…

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

Qwen3-80B:80B

Speed
26/50
TTFT
20/20
Memory
13/30

Quality

google/gemma-4-26b-a4b-…

Reasoning
18/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Qwen3-80B:80B

Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
13/15
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