Back to leaderboard

qwen3.5-27b

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score
26 vs 88
Hardware Fit
63 vs 80
Quality Score
10 vs 92

Hardware

qwen3.5-27b gemma4:26b
MachineMac miniASUSTeK COMPUTER INC. GX10
CPUApple M4 ProCortex-X925
Cores1420
RAM64 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5-27b gemma4:26b
Tokens/sec9.566.7
First chunk1099 ms583 ms
TTFT1.1 s30.0 s
Load timeN/A6.7 s
Memory usage16.3 GB17.6 GB
Memory %25%15%

HW Fit Score Breakdown

qwen3.5-27b

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

gemma4:26b

Speed
50/50
TTFT
0/20
Memory
30/30

Quality

qwen3.5-27b

Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
7/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate

gemma4:26b

Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
14/15
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