qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
qwen2.5:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Mar 16, 2026 · Intel Core™ i7-4771
Global Score
59 vs 65
Hardware Fit
63 vs 92
Quality Score
58 vs 54
Hardware
qwen3.8-27b-mlx qwen2.5:1.5b
MachineMacBook ProiMac
CPUApple M5 MaxIntel Core™ i7-4771
Cores188
RAM64 GB32 GB
GPUApple M5 MaxNVIDIA GeForce GTX 780M
OSmacOS 27.0macOS 15.7.3
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx qwen2.5:1.5b
Tokens/sec18.319.6
First chunk4 ms690 ms
TTFT530 ms690 ms
Load timeN/A21.4 s
Memory usage38.5 GB1.0 GB
Memory %60%3%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
qwen2.5:1.5b
Speed
42/50
TTFT
20/20
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
qwen2.5:1.5b
Reasoning
8/20
Coding
9/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
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