Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
82 vs 66
Hardware Fit
90 vs 91
Quality Score
79 vs 55

Hardware

qwen3:14b qwen3.8-27b-mlx
MachineMicro-Star International Co., Ltd. MS-7C37MacBook Pro
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M5 Max
Cores2418
RAM64 GB64 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080Apple M5 Max
OSMicrosoft Windows 11 专业版 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:14b qwen3.8-27b-mlx
Tokens/sec74.433.2
First chunk324 ms7 ms
TTFT2.6 s311 ms
Load time5.1 sN/A
Memory usage9.0 GB0.5 GB
Memory %14%1%

HW Fit Score Breakdown

qwen3:14b

Speed
50/50
TTFT
10/20
Memory
30/30

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

Quality

qwen3:14b

Reasoning
18/20
Coding
11/20
Instruction
17/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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

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