Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

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

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jul 29, 2026 · Intel Xeon® E5-2637 v3

Global Score
82 vs 83
Hardware Fit
90 vs 66
Quality Score
79 vs 90

Hardware

qwen3:14b qwen3:30b-a3b-inst…
MachineMicro-Star International Co., Ltd. MS-7C37Dell Inc. Precision Tower 7910
CPUAMD Ryzen 9 3900X 12-Core ProcessorIntel Xeon® E5-2637 v3
Cores2416
RAM64 GB96 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080NVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 专业版 10.0.26200Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:14b qwen3:30b-a3b-inst…
Tokens/sec74.417.7
First chunk324 ms1244 ms
TTFT2.6 s1.2 s
Load time5.1 s20.5 s
Memory usage9.0 GB20.6 GB
Memory %14%21%

HW Fit Score Breakdown

qwen3:14b

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

qwen3:30b-a3b-instruct-…

Speed
19/50
TTFT
17/20
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

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong 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