qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 2, 2026 · Apple M4
gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
Global Score
47 vs 83
Hardware Fit
67 vs 64
Quality Score
38 vs 91
Hardware
qwen3:8b gpt-oss:120b
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.5 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3:8b gpt-oss:120b
Tokens/sec18.728.6
First chunkN/A422 ms
TTFT12.1 s2.5 s
Load time1.2 s9.9 s
Memory usage9.5 GB60.1 GB
Memory %30%49%
HW Fit Score Breakdown
qwen3:8b
Speed
31/50
TTFT
6/20
Memory
30/30
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
Quality
qwen3:8b
Reasoning
5/20
Coding
5/20
Instruction
4/20
Structured
12/15
Math
2/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Poor Structured Output: Strong Math: Poor Multilingual: Strong
gpt-oss:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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