gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
gemma-3-27b-it-qat
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 5, 2026 · Apple M4 Pro
Global Score
84 vs 76
Hardware Fit
69 vs 51
Quality Score
91 vs 87
Hardware
gptoss · 20.9B · M… gemma-3-27b-it-qat
MachineMac ProMac mini
CPUIntel Core™ i5-10400Apple M4 Pro
Cores1214
RAM32 GB64 GB
GPUAMD Radeon RX 6700 XTApple M4 Pro
OSmacOS 26.5.1macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced
Performance
gptoss · 20.9B · M… gemma-3-27b-it-qat
Tokens/sec17.58.9
First chunk643 ms3976 ms
TTFT7.7 s4.0 s
Load time0.0 sN/A
Memory usage0.8 GB15.7 GB
Memory %3%25%
HW Fit Score Breakdown
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
Memory
30/30
gemma-3-27b-it-qat
Speed
12/50
TTFT
9/20
Memory
30/30
Quality
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma-3-27b-it-qat
Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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