deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
qwen2.5:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Global Score
64 vs 65
Hardware Fit
98 vs 87
Quality Score
49 vs 56
Hardware
deepscaler:1.5b qwen2.5:1.5b
MachineMicrosoft WSLShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUAMD Ryzen 5 5500ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores128
RAM8 GB30 GB
GPUIntegrated / UnknownZX C-1190
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26100
Archx64x64
Power Modeunknownbalanced
Performance
deepscaler:1.5b qwen2.5:1.5b
Tokens/sec104.616.8
First chunk849 ms941 ms
TTFT850 ms941 ms
Load time10.5 s0.2 s
Memory usage3.0 GB1.0 GB
Memory %40%3%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
qwen2.5:1.5b
Speed
37/50
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
qwen2.5:1.5b
Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
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