gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
Global Score
94 vs 59
Hardware Fit
91 vs 63
Quality Score
95 vs 58
Hardware
gpt-oss:20b qwen3.8-27b-mlx
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M5 Max
Cores3218
RAM64 GB64 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M5 Max
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b qwen3.8-27b-mlx
Tokens/sec48.018.3
First chunk357 ms4 ms
TTFT2.3 s530 ms
Load time0.2 sN/A
Memory usage16.4 GB38.5 GB
Memory %26%60%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
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-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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