qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
smollm2:1.7b
OLLAMA GGUFllama · 1.7B · Q8_0
Mar 2, 2026 · Apple M4
Global Score
66 vs 64
Hardware Fit
91 vs 100
Quality Score
55 vs 49
Hardware
qwen3.8-27b-mlx smollm2:1.7b
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 smollm2:1.7b
Tokens/sec33.251.8
First chunk7 msN/A
TTFT311 ms84 ms
Load timeN/A0.4 s
Memory usage0.5 GB3.7 GB
Memory %1%12%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
smollm2:1.7b
Speed
40/50
TTFT
30/20
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
smollm2:1.7b
Reasoning
7/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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