deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
qwen2.5-coder:3b
OLLAMA GGUFqwen2 · 3.1B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
64 vs 73
Hardware Fit
98 vs 100
Quality Score
49 vs 61
Hardware
deepscaler:1.5b qwen2.5-coder:3b
MachineMicrosoft WSLNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 5 5500Cortex-A78AE
Cores126
RAM8 GB7 GB
GPUIntegrated / UnknownIntegrated / Unknown
OSUbuntu 26.04.1 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modeunknownbalanced
Performance
deepscaler:1.5b qwen2.5-coder:3b
Tokens/sec104.621.3
First chunk849 ms969 ms
TTFT850 ms969 ms
Load time10.5 s6.6 s
Memory usage3.0 GB2.0 GB
Memory %40%27%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
qwen2.5-coder:3b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
deepscaler:1.5b
Reasoning
10/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
11/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Weak
qwen2.5-coder:3b
Reasoning
8/20
Coding
15/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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