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-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Good

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
93 vs 78
Hardware Fit
96 vs 56
Quality Score
92 vs 87

Hardware

google/gemma-4-26b… qwen3.8-27b-uncens…
MachineMicro-Star International Co., Ltd. MS-7E51System manufacturer
CPUAMD Ryzen 7 9700X 8-Core ProcessorAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM31 GB31 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsNavi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedperformance

Performance

google/gemma-4-26b… qwen3.8-27b-uncens…
Tokens/sec109.77.0
First chunk29 ms19 ms
TTFT156 ms1.2 s
Load timeN/AN/A
Memory usage14.6 GB15.6 GB
Memory %47%50%

HW Fit Score Breakdown

google/gemma-4-26b-a4b-…

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

qwen3.8-27b-uncensored-…

Speed
11/50
TTFT
20/20
Memory
25/30

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-uncensored-…

Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View google/gemma-4-26b… details | View qwen3.8-27b-uncens… 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