Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

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

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

Global Score
82 vs 80
Hardware Fit
90 vs 100
Quality Score
79 vs 71

Hardware

qwen3:14b gemma-3-4b-it-q4-k-m
MachineMicro-Star International Co., Ltd. MS-7C37Mac Pro
CPUAMD Ryzen 9 3900X 12-Core ProcessorIntel Core™ i5-10400
Cores2412
RAM64 GB32 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080AMD Radeon RX 6700 XT
OSMicrosoft Windows 11 专业版 10.0.26200macOS 26.5.1
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:14b gemma-3-4b-it-q4-k-m
Tokens/sec74.475.0
First chunk324 ms136 ms
TTFT2.6 s136 ms
Load time5.1 s0.0 s
Memory usage9.0 GB0.8 GB
Memory %14%3%

HW Fit Score Breakdown

qwen3:14b

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

gemma-3-4b-it-q4-k-m

Speed
50/50
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

gemma-3-4b-it-q4-k-m

Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3:14b details | View gemma-3-4b-it-q4-k-m details

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