gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
llama3:latest
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
83 vs 71
Hardware Fit
64 vs 95
Quality Score
91 vs 60
Hardware
gpt-oss:120b llama3:latest
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 llama3:latest
Tokens/sec28.622.3
First chunk422 msN/A
TTFT2.5 s295 ms
Load time9.9 s0.8 s
Memory usage60.1 GB5.6 GB
Memory %49%18%
HW Fit Score Breakdown
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
llama3:latest
Speed
35/50
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
llama3:latest
Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong 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