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

Qwen3.8-27B-Ridge-3.7bpw_empero.ai:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ2_M

Good

Aug 27, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
93 vs 75
Hardware Fit
96 vs 99
Quality Score
92 vs 64

Hardware

google/gemma-4-26b… Qwen3.8-27B-Ridge-…
MachineMicro-Star International Co., Ltd. MS-7E51Micro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 7 9700X 8-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM31 GB31 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-26b… Qwen3.8-27B-Ridge-…
Tokens/sec109.760.3
First chunk29 ms154 ms
TTFT156 ms154 ms
Load timeN/A0.0 s
Memory usage14.6 GB11.0 GB
Memory %47%35%

HW Fit Score Breakdown

google/gemma-4-26b-a4b-…

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

Qwen3.8-27B-Ridge-3.7bp…

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

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

Qwen3.8-27B-Ridge-3.7bp…

Reasoning
20/20
Coding
17/20
Instruction
6/20
Structured
1/15
Math
14/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate

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