gpt-oss-safeguard-20b-mlx
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 12, 2026 · Apple M4
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
87 vs 86
Hardware Fit
82 vs 78
Quality Score
89 vs 89
Hardware
gpt-oss-safeguard-… Kimi-48B:48B
MachineMac miniGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM24 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss-safeguard-… Kimi-48B:48B
Tokens/sec41.422.8
First chunk8 ms721 ms
TTFT3.6 s721 ms
Load timeN/A23.0 s
Memory usage14.5 GB25.5 GB
Memory %61%40%
HW Fit Score Breakdown
gpt-oss-safeguard-20b-mlx
Speed
50/50
TTFT
12/20
Memory
20/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
gpt-oss-safeguard-20b-mlx
Reasoning
19/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
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