qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
59 vs 67
Hardware Fit
63 vs 21
Quality Score
58 vs 87
Hardware
qwen3.8-27b-mlx GPT-120B:120b
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M5 MaxIntel Core™ Ultra X7 358H
Cores1816
RAM64 GB64 GB
GPUApple M5 MaxIntel(R) Arc(TM) B390 GPU
OSmacOS 27.0Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx GPT-120B:120b
Tokens/sec18.311.8
First chunk4 ms4674 ms
TTFT530 ms9.3 s
Load timeN/A77.6 s
Memory usage38.5 GB61.0 GB
Memory %60%96%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
GPT-120B:120b
Speed
15/50
TTFT
4/20
Memory
2/30
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-120B:120b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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