gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
May 25, 2026 · Apple M4 Pro
qwen3.8:27b-q8_0
OLLAMA GGUFqwen35 · 27.3B · Q8_0
Aug 22, 2026 · AMD EPYC 7713 64-Core Processor
Global Score
94 vs 89
Hardware Fit
92 vs 88
Quality Score
95 vs 89
Hardware
gpt-oss:20b qwen3.8:27b-q8_0
MachineMacBook ProDell Inc. PowerEdge XE8545
CPUApple M4 ProAMD EPYC 7713 64-Core Processor
Cores14128
RAM48 GB1007 GB
GPUApple M4 ProGA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OSmacOS 26.4.1Rocky Linux 8.10
Archarm64x64
Power Modebalancedunknown
Performance
gpt-oss:20b qwen3.8:27b-q8_0
Tokens/sec54.539.9
First chunk318 ms192 ms
TTFT2.9 s192 ms
Load time4.0 s19.0 s
Memory usage16.4 GB51.0 GB
Memory %34%5%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
13/20
Memory
29/30
qwen3.8:27b-q8_0
Speed
38/50
TTFT
20/20
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
qwen3.8:27b-q8_0
Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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