codellama:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 1, 2026 · Apple M4
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 11, 2026 · Apple M4
Global Score
63 vs 95
Hardware Fit
97 vs 99
Quality Score
49 vs 93
Hardware
codellama:7b 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
codellama:7b openai/gpt-oss-20b
Tokens/sec23.629.3
First chunkN/A21 ms
TTFT297 ms1.8 s
Load time0.9 s18.5 s
Memory usage12.6 GB0.0 GB
Memory %39%0%
HW Fit Score Breakdown
codellama:7b
Speed
37/50
TTFT
30/20
Memory
30/30
openai/gpt-oss-20b
Speed
50/50
TTFT
19/20
Memory
30/30
Quality
codellama:7b
Reasoning
6/20
Coding
7/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
openai/gpt-oss-20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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