openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
deepseek-coder-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
91 vs 83
Hardware Fit
90 vs 100
Quality Score
91 vs 75
Hardware
openai/gpt-oss-20b deepseek-coder-v2:…
MachineMacBook ProGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M3 MaxIntel Core™ i5-14400F
Cores1616
RAM128 GB32 GB
GPUApple M3 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 27.2Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b deepseek-coder-v2:…
Tokens/sec95.1150.4
First chunk3 ms116 ms
TTFT2.5 s116 ms
Load time9.2 s5.8 s
Memory usage0.0 GB9.4 GB
Memory %0%30%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
deepseek-coder-v2:16b
Speed
50/50
TTFT
20/20
Memory
30/30
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
deepseek-coder-v2:16b
Reasoning
10/20
Coding
18/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate 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