qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
gpt-oss-safeguard-20b-mlx
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 12, 2026 · Apple M4
Global Score
81 vs 87
Hardware Fit
95 vs 82
Quality Score
75 vs 89
Hardware
qwen3:8b gpt-oss-safeguard-…
MachineASUSMac mini
CPUIntel Core™ i5-14600KFApple M4
Cores2010
RAM32 GB24 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M4
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:8b gpt-oss-safeguard-…
Tokens/sec108.341.4
First chunk169 ms8 ms
TTFT169 ms3.6 s
Load time1.7 sN/A
Memory usage5.6 GB14.5 GB
Memory %18%61%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
20/20
Memory
25/30
gpt-oss-safeguard-20b-mlx
Speed
50/50
TTFT
12/20
Memory
20/30
Quality
qwen3:8b
Reasoning
15/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
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
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