Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Aug 15, 2026 · AMD RYZEN AI MAX+ 395

Gemma4-26B:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Excellent

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

Global Score
80 vs 87
Hardware Fit
66 vs 82
Quality Score
86 vs 89

Hardware

qwen3.8:27b Gemma4-26B:26b
MachineAZW GTR ProGMKtec NucBox EVO-T2S
CPUAMD RYZEN AI MAX+ 395Intel Core™ Ultra X7 358H
Cores3216
RAM125 GB64 GB
GPURadeon 8060SIntel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.8:27b Gemma4-26B:26b
Tokens/sec18.423.4
First chunk587 ms1073 ms
TTFT587 ms1.1 s
Load time7.4 s16.0 s
Memory usage17.4 GB16.7 GB
Memory %14%26%

HW Fit Score Breakdown

qwen3.8:27b

Speed
17/50
TTFT
19/20
Memory
30/30

Gemma4-26B:26b

Speed
32/50
TTFT
20/20
Memory
30/30

Quality

qwen3.8:27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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

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