qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
59 vs 93
Hardware Fit
63 vs 85
Quality Score
58 vs 96
Hardware
qwen3.8-27b-mlx gpt-oss:20b
MachineMacBook ProAZW GTR Pro
CPUApple M5 MaxAMD RYZEN AI MAX+ 395
Cores1832
RAM64 GB125 GB
GPUApple M5 MaxAMD Radeon 8060S
OSmacOS 27.0Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3.8-27b-mlx gpt-oss:20b
Tokens/sec18.347.1
First chunk4 ms320 ms
TTFT530 ms1.8 s
Load timeN/A3.8 s
Memory usage38.5 GB16.4 GB
Memory %60%13%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
gpt-oss:20b
Speed
44/50
TTFT
11/20
Memory
30/30
Quality
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
gpt-oss:20b
Reasoning
19/20
Coding
19/20
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
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