qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
Global Score
59 vs 65
Hardware Fit
63 vs 99
Quality Score
58 vs 51
Hardware
qwen3.8-27b-mlx smollm2-1.7b-instr…
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-instr…
Tokens/sec18.328.5
First chunk4 ms393 ms
TTFT530 ms393 ms
Load timeN/AN/A
Memory usage38.5 GB3.2 GB
Memory %60%10%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
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
smollm2-1.7b-instruct
Reasoning
10/20
Coding
10/20
Instruction
13/20
Structured
11/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate 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