gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
94 vs 72
Hardware Fit
91 vs 71
Quality Score
95 vs 72
Hardware
gpt-oss:20b ministral-3:8b
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM64 GB16 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M1 Pro
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b ministral-3:8b
Tokens/sec48.019.8
First chunk357 ms269 ms
TTFT2.3 s269 ms
Load time0.2 s10.7 s
Memory usage16.4 GB13.7 GB
Memory %26%86%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
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
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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