openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Sep 29, 2026 · Apple M5 Max
nemotron-3-nano:latest
OLLAMA GGUFnemotron_h_moe · 31.6B · Q4_K_M
Mar 27, 2026 · AMD RYZEN AI MAX+ 395
Global Score
83 vs 89
Hardware Fit
80 vs 100
Quality Score
84 vs 84
Hardware
openai/gpt-oss-20b nemotron-3-nano:la…
MachineMacBook ProAZW GTR Pro
CPUApple M5 MaxAMD RYZEN AI MAX+ 395
Cores1832
RAM128 GB125 GB
GPUApple M5 MaxRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
openai/gpt-oss-20b nemotron-3-nano:la…
Tokens/sec138.465.2
First chunk3 ms295 ms
TTFT30.0 s295 ms
Load time6.8 s8.7 s
Memory usage0.5 GB26.0 GB
Memory %0%21%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
30/30
nemotron-3-nano:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
nemotron-3-nano:latest
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest