Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jul 3, 2026 · AMD RYZEN AI MAX+ 395

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

Global Score
94 vs 95
Hardware Fit
91 vs 94
Quality Score
95 vs 96

Hardware

gpt-oss:20b qwen3-30b-a3b-thin…
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)Mac Studio
CPUAMD RYZEN AI MAX+ 395Apple M2 Max
Cores3212
RAM64 GB96 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M2 Max
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

gpt-oss:20b qwen3-30b-a3b-thin…
Tokens/sec48.080.4
First chunk357 ms46 ms
TTFT2.3 s1.8 s
Load time0.2 sN/A
Memory usage16.4 GB21.2 GB
Memory %26%22%

HW Fit Score Breakdown

gpt-oss:20b

Speed
50/50
TTFT
11/20
Memory
30/30

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

Quality

gpt-oss:20b

Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
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