gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
nemotron-3.5-bolt:74b-a9b-iq2
OLLAMA GGUFnemotron_h_moe · 74.0B · IQ2_XXS
Oct 16, 2026 · AMD RYZEN AI MAX+ 395
Global Score
83 vs 90
Hardware Fit
65 vs 96
Quality Score
90 vs 87
Hardware
gpt-oss:20b nemotron-3.5-bolt:…
MachineMac miniAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB125 GB
GPUApple M4Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.5 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gpt-oss:20b nemotron-3.5-bolt:…
Tokens/sec17.149.9
First chunk705 ms370 ms
TTFT10.2 s370 ms
Load time23.1 s7.6 s
Memory usage13.1 GB3.9 GB
Memory %55%3%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
nemotron-3.5-bolt:74b-a…
Speed
46/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
nemotron-3.5-bolt:74b-a…
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest