Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

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

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
82 vs 89
Hardware Fit
90 vs 97
Quality Score
79 vs 86

Hardware

qwen3:14b qwen/qwen3.6-35b-a3b
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 qwen/qwen3.6-35b-a3b
Tokens/sec74.4130.2
First chunk324 ms5 ms
TTFT2.6 s135 ms
Load time5.1 sN/A
Memory usage9.0 GB26.6 GB
Memory %14%42%

HW Fit Score Breakdown

qwen3:14b

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

qwen/qwen3.6-35b-a3b

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

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

qwen/qwen3.6-35b-a3b

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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