Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Not Rec.

Mar 19, 2026 · Apple M4

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
77 vs 72
Hardware Fit
67 vs 35
Quality Score
81 vs 88

Hardware

openai/gpt-oss-20b qwen/qwen3.5-35b-a3b
MachineMac miniSystem manufacturer
CPUApple M4AMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM24 GB32 GB
GPUApple M4AMD Radeon RX 9060 XT
OSmacOS 26.3Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

openai/gpt-oss-20b qwen/qwen3.5-35b-a3b
Tokens/sec30.58.3
First chunk18 ms32 ms
TTFT30.0 s2.0 s
Load timeN/AN/A
Memory usage15.8 GB28.9 GB
Memory %66%91%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
0/20
Memory
17/30

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

Quality

openai/gpt-oss-20b

Reasoning
19/20
Coding
11/20
Instruction
12/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest