Back to leaderboard

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

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

Global Score
60 vs 82
Hardware Fit
90 vs 90
Quality Score
47 vs 79

Hardware

deepseek-r1:1.5b qwen3:14b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMicro-Star International Co., Ltd. MS-7C37
CPUCortex-A78AEAMD Ryzen 9 3900X 12-Core Processor
Cores624
RAM7 GB64 GB
GPUIntegrated / UnknownGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 专业版 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

deepseek-r1:1.5b qwen3:14b
Tokens/sec34.674.4
First chunk5314 ms324 ms
TTFT5.3 s2.6 s
Load time5.1 s5.1 s
Memory usage1.1 GB9.0 GB
Memory %15%14%

HW Fit Score Breakdown

deepseek-r1:1.5b

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

qwen3:14b

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

Quality

deepseek-r1:1.5b

Reasoning
11/20
Coding
6/20
Instruction
7/20
Structured
4/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Weak

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

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