qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 18, 2026 · Apple M4 Max
smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
Global Score
81 vs 65
Hardware Fit
68 vs 99
Quality Score
87 vs 51
Hardware
qwen/qwen3.8-27b smollm2-1.7b-instr…
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM128 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.8-27b smollm2-1.7b-instr…
Tokens/sec16.428.5
First chunk5 ms393 ms
TTFT742 ms393 ms
Load timeN/AN/A
Memory usage38.5 GB3.2 GB
Memory %30%10%
HW Fit Score Breakdown
qwen/qwen3.8-27b
Speed
18/50
TTFT
20/20
Memory
30/30
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
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
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