gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
83 vs 80
Hardware Fit
64 vs 100
Quality Score
91 vs 71
Hardware
gpt-oss:120b gemma3:4b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.5 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced
Performance
gpt-oss:120b gemma3:4b
Tokens/sec28.634.6
First chunk422 msN/A
TTFT2.5 s303 ms
Load time9.9 s1.2 s
Memory usage60.1 GB4.6 GB
Memory %49%14%
HW Fit Score Breakdown
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
gemma3:4b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
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
gemma3:4b
Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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