Back to leaderboard

qwen3.8-27b-claude-opus-reasoning-distilled

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Aug 20, 2026 · Apple M4 Max

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

Global Score
80 vs 70
Hardware Fit
63 vs 93
Quality Score
87 vs 60

Hardware

qwen3.8-27b-claude… qwen3.5-2b-mlx
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

qwen3.8-27b-claude… qwen3.5-2b-mlx
Tokens/sec24.032.9
First chunk20 ms3096 ms
TTFT4.5 s3.1 s
Load timeN/AN/A
Memory usage15.7 GB2.5 GB
Memory %12%8%

HW Fit Score Breakdown

qwen3.8-27b-claude-opus…

Speed
27/50
TTFT
6/20
Memory
30/30

qwen3.5-2b-mlx

Speed
50/50
TTFT
13/20
Memory
30/30

Quality

qwen3.8-27b-claude-opus…

Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-2b-mlx

Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

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