gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
May 25, 2026 · Apple M4 Pro
prism-ml/bonsai-27b
LM-STUDIO GGUFqwen35 · 27B · Q1_0
Sep 20, 2026 · AMD Ryzen 9 8940HX
Global Score
94 vs 81
Hardware Fit
92 vs 95
Quality Score
95 vs 75
Hardware
gpt-oss:20b prism-ml/bonsai-27b
MachineMacBook ProASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUApple M4 ProAMD Ryzen 9 8940HX
Cores1432
RAM48 GB15 GB
GPUApple M4 ProNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSmacOS 26.4.1Microsoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b prism-ml/bonsai-27b
Tokens/sec54.533.6
First chunk318 ms20 ms
TTFT2.9 s409 ms
Load time4.0 sN/A
Memory usage16.4 GB5.3 GB
Memory %34%35%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
13/20
Memory
29/30
prism-ml/bonsai-27b
Speed
46/50
TTFT
20/20
Memory
29/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
prism-ml/bonsai-27b
Reasoning
17/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate 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