qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 25, 2026 · Apple M1 Pro
Global Score
59 vs 76
Hardware Fit
63 vs 100
Quality Score
58 vs 66
Hardware
qwen3.8-27b-mlx hf.co/empero-ai/Qw…
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M1 Pro
Cores1810
RAM64 GB16 GB
GPUApple M5 MaxApple M1 Pro
OSmacOS 27.0macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx hf.co/empero-ai/Qw…
Tokens/sec18.340.3
First chunk4 ms101 ms
TTFT530 ms101 ms
Load timeN/A2.7 s
Memory usage38.5 GB4.5 GB
Memory %60%28%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
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
hf.co/empero-ai/Qwen3.8…
Reasoning
11/20
Coding
10/20
Instruction
12/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate 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