Back to leaderboard

GPT-OSS-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 18, 2026 · Intel Core™ i7-14700F

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 6bit

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
93 vs 87
Hardware Fit
92 vs 90
Quality Score
93 vs 86

Hardware

GPT-OSS-20B:20b qwen/qwen3.6-35b-a3b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M5 Max
Cores2818
RAM128 GB64 GB
GPUNVIDIA GeForce RTX 5080Apple M5 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

GPT-OSS-20B:20b qwen/qwen3.6-35b-a3b
Tokens/sec178.686.5
First chunk695 ms9 ms
TTFT1.4 s175 ms
Load time31.2 sN/A
Memory usage11.9 GB37.9 GB
Memory %9%59%

HW Fit Score Breakdown

GPT-OSS-20B:20b

Speed
50/50
TTFT
12/20
Memory
30/30

qwen/qwen3.6-35b-a3b

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

Quality

GPT-OSS-20B: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

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
15/20
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