Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 11, 2026 · Apple M4

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
95 vs 65
Hardware Fit
99 vs 73
Quality Score
93 vs 62

Hardware

openai/gpt-oss-20b qwen3.5:4b
MachineMac miniAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB125 GB
GPUApple M4AMD Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

openai/gpt-oss-20b qwen3.5:4b
Tokens/sec29.345.7
First chunk21 ms180 ms
TTFT1.8 s30.0 s
Load time18.5 s5.3 s
Memory usage0.0 GB16.2 GB
Memory %0%13%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
19/20
Memory
30/30

qwen3.5:4b

Speed
43/50
TTFT
0/20
Memory
30/30

Quality

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

qwen3.5:4b

Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong
View openai/gpt-oss-20b details | View qwen3.5:4b details

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