deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Qwen3-Coder-30B:30B
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
60 vs 88
Hardware Fit
90 vs 91
Quality Score
47 vs 87
Hardware
deepseek-r1:1.5b Qwen3-Coder-30B:30B
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperGMKtec NucBox EVO-T2S
CPUCortex-A78AEIntel Core™ Ultra X7 358H
Cores616
RAM7 GB64 GB
GPUIntegrated / UnknownIntel(R) Arc(TM) B390 GPU
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
deepseek-r1:1.5b Qwen3-Coder-30B:30B
Tokens/sec34.632.2
First chunk5314 ms540 ms
TTFT5.3 s540 ms
Load time5.1 s15.6 s
Memory usage1.1 GB17.7 GB
Memory %15%28%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
50/50
TTFT
10/20
Memory
30/30
Qwen3-Coder-30B:30B
Speed
41/50
TTFT
20/20
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-Coder-30B:30B
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest