gpt-oss-safeguard-20b-mlx
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 12, 2026 · Apple M4
qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
87 vs 55
Hardware Fit
82 vs 87
Quality Score
89 vs 41
Hardware
gpt-oss-safeguard-… qwen3.5-0.8b-mlx
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss-safeguard-… qwen3.5-0.8b-mlx
Tokens/sec41.468.2
First chunk8 ms3268 ms
TTFT3.6 s3.3 s
Load timeN/AN/A
Memory usage14.5 GB0.6 GB
Memory %61%2%
HW Fit Score Breakdown
gpt-oss-safeguard-20b-mlx
Speed
50/50
TTFT
12/20
Memory
20/30
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
13/20
Memory
24/30
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
qwen3.5-0.8b-mlx
Reasoning
8/20
Coding
1/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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