unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
84 vs 95
Hardware Fit
64 vs 98
Quality Score
92 vs 94
Hardware
unsloth/gemma-4-26… gpt-oss:20b
MachineMac miniASUS
CPUApple M4Intel Core™ Ultra 9 285K
Cores1024
RAM24 GB47 GB
GPUApple M4NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
unsloth/gemma-4-26… gpt-oss:20b
Tokens/sec16.5239.9
First chunk32 ms180 ms
TTFT2.2 s616 ms
Load timeN/A4.3 s
Memory usage19.3 GB13.9 GB
Memory %80%29%
HW Fit Score Breakdown
unsloth/gemma-4-26b-a4b…
Speed
36/50
TTFT
18/20
Memory
10/30
gpt-oss:20b
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
unsloth/gemma-4-26b-a4b…
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
15/15
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest