Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
90 vs 65
Hardware Fit
88 vs 88
Quality Score
91 vs 55

Hardware

openai/gpt-oss-20b qwen3.5-2b-mlx
MachineASUSMac mini
CPUAMD Ryzen 5 5500Apple M4 Pro
Cores1214
RAM31 GB64 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4 Pro
OSNobara Linux 43macOS 15.7.4
Archx64arm64
Power Modeperformancebalanced

Performance

openai/gpt-oss-20b qwen3.5-2b-mlx
Tokens/sec58.748.9
First chunk6 ms4208 ms
TTFT4.5 s4.2 s
Load timeN/AN/A
Memory usage11.9 GB1.6 GB
Memory %38%3%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
10/20
Memory
28/30

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
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: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest