openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
91 vs 80
Hardware Fit
90 vs 62
Quality Score
91 vs 88
Hardware
openai/gpt-oss-20b qwen3.5-35b-a3b
MachineMacBook ProDocker Container
CPUApple M3 MaxIntel Gen Intel® Core™ i9-11900H
Cores1616
RAM128 GB15 GB
GPUApple M3 MaxTigerLake-H GT1 [UHD Graphics]
OSmacOS 27.2Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
openai/gpt-oss-20b qwen3.5-35b-a3b
Tokens/sec95.110.6
First chunk3 ms52 ms
TTFT2.5 s3.2 s
Load time9.2 s7.6 s
Memory usage0.0 GB1.1 GB
Memory %0%7%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
qwen3.5-35b-a3b
Speed
19/50
TTFT
13/20
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
qwen3.5-35b-a3b
Reasoning
16/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
11/15
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