Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

smollm2-1.7b-instruct

LM-STUDIO MLX

llama · 1.7B · bf16

Good

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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest