deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
64 vs 68
Hardware Fit
98 vs 59
Quality Score
49 vs 72
Hardware
deepscaler:1.5b qwen2.5-coder:7b
MachineMicrosoft WSLASUS
CPUAMD Ryzen 5 5500Intel Gen Intel® Core™ i7-13700K
Cores1224
RAM8 GB64 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3070
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeunknownunknown
Performance
deepscaler:1.5b qwen2.5-coder:7b
Tokens/sec104.634.4
First chunk849 ms1991 ms
TTFT850 ms2.0 s
Load time10.5 s40.6 s
Memory usage3.0 GB5.0 GB
Memory %40%8%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
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:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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