qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Oct 20, 2026 · Apple M1 Pro
qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 18, 2026 · Apple M4 Max
Global Score
78 vs 81
Hardware Fit
56 vs 68
Quality Score
87 vs 87
Hardware
qwen3.8-27b-mlx qwen/qwen3.8-27b
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M4 Max
Cores1016
RAM32 GB128 GB
GPUApple M1 ProApple M4 Max
OSmacOS 15.6.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx qwen/qwen3.8-27b
Tokens/sec10.816.4
First chunk8 ms5 ms
TTFT2.6 s742 ms
Load timeN/AN/A
Memory usage21.0 GB38.5 GB
Memory %66%30%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
16/20
Memory
17/30
qwen/qwen3.8-27b
Speed
18/50
TTFT
20/20
Memory
30/30
Quality
qwen3.8-27b-mlx
Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen/qwen3.8-27b
Reasoning
17/20
Coding
18/20
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