granite3.1-dense:2b
OLLAMA GGUFgranite · 2.5B · Q4_K_M
Mar 2, 2026 · Apple M4
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Apr 1, 2026 · Apple M4
Global Score
68 vs 82
Hardware Fit
100 vs 85
Quality Score
54 vs 81
Hardware
granite3.1-dense:2b openai/gpt-oss-20b
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
granite3.1-dense:2b openai/gpt-oss-20b
Tokens/sec54.631.8
First chunkN/A32 ms
TTFT121 ms8.4 s
Load time0.4 s22.7 s
Memory usage5.6 GB0.0 GB
Memory %18%0%
HW Fit Score Breakdown
granite3.1-dense:2b
Speed
40/50
TTFT
30/20
Memory
30/30
openai/gpt-oss-20b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
granite3.1-dense:2b
Reasoning
8/20
Coding
9/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
openai/gpt-oss-20b
Reasoning
19/20
Coding
14/20
Instruction
9/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak 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