Back to leaderboard

gpt-oss-20b

LM-STUDIO GGUF
Excellent

Mar 6, 2026 · Apple M4 Pro

nemotron-3.5-lightning:latest

OLLAMA GGUF

nemotron_h_moe · 32.9B · Q4_K_M

Not Rec.

Aug 17, 2026 · Cortex-X925

Global Score
95 vs 87
Hardware Fit
94 vs 80
Quality Score
95 vs 90

Hardware

gpt-oss-20b nemotron-3.5-light…
MachineMac miniASUSTeK COMPUTER INC. GX10
CPUApple M4 ProCortex-X925
Cores1420
RAM64 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

gpt-oss-20b nemotron-3.5-light…
Tokens/sec118.284.1
First chunk471 ms371 ms
TTFT2.2 s30.0 s
Load timeN/A0.3 s
Memory usage11.3 GB24.9 GB
Memory %18%20%

HW Fit Score Breakdown

gpt-oss-20b

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

nemotron-3.5-lightning:…

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

Quality

gpt-oss-20b

Reasoning
19/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

nemotron-3.5-lightning:…

Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gpt-oss-20b details | View nemotron-3.5-light… 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