qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
deepseek-r1:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
66 vs 77
Hardware Fit
91 vs 94
Quality Score
55 vs 70
Hardware
qwen3.8-27b-mlx deepseek-r1:7b
MachineMacBook ProMacBook Air
CPUApple M5 MaxApple M4
Cores1810
RAM64 GB32 GB
GPUApple M5 MaxApple M4
OSmacOS 27.0macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx deepseek-r1:7b
Tokens/sec33.222.2
First chunk7 ms285 ms
TTFT311 ms285 ms
Load timeN/A0.8 s
Memory usage0.5 GB7.6 GB
Memory %1%24%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
deepseek-r1:7b
Speed
44/50
TTFT
20/20
Memory
30/30
Quality
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
deepseek-r1:7b
Reasoning
14/20
Coding
12/20
Instruction
10/20
Structured
12/15
Math
15/15
Multilingual
7/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong 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