Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 11, 2026 · Apple M4

qwen3.6:35b-a3b-q8_0

OLLAMA GGUF

qwen35moe · 36.0B · Q8_0

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score
95 vs 80
Hardware Fit
99 vs 79
Quality Score
93 vs 81

Hardware

openai/gpt-oss-20b qwen3.6:35b-a3b-q8_0
MachineMac miniASUSTeK COMPUTER INC. GX10
CPUApple M4Cortex-X925
Cores1020
RAM24 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

openai/gpt-oss-20b qwen3.6:35b-a3b-q8_0
Tokens/sec29.355.5
First chunk21 ms528 ms
TTFT1.8 s30.0 s
Load time18.5 s32.6 s
Memory usage0.0 GB41.0 GB
Memory %0%34%

HW Fit Score Breakdown

openai/gpt-oss-20b

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

qwen3.6:35b-a3b-q8_0

Speed
50/50
TTFT
0/20
Memory
29/30

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

qwen3.6:35b-a3b-q8_0

Reasoning
18/20
Coding
13/20
Instruction
17/20
Structured
10/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
View openai/gpt-oss-20b details | View qwen3.6:35b-a3b-q8_0 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