openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
91 vs 68
Hardware Fit
90 vs 59
Quality Score
91 vs 72
Hardware
openai/gpt-oss-20b qwen2.5-coder:7b
MachineMacBook ProASUS
CPUApple M3 MaxIntel Gen Intel® Core™ i7-13700K
Cores1624
RAM128 GB64 GB
GPUApple M3 MaxNVIDIA GeForce RTX 3070
OSmacOS 27.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
openai/gpt-oss-20b qwen2.5-coder:7b
Tokens/sec95.134.4
First chunk3 ms1991 ms
TTFT2.5 s2.0 s
Load time9.2 s40.6 s
Memory usage0.0 GB5.0 GB
Memory %0%8%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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