deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
nemotron-3-super:latest
OLLAMA GGUFnemotron_h_moe · 123.6B · Q4_K_M
Oct 3, 2026 · Cortex-X925
Global Score
64 vs 74
Hardware Fit
98 vs 50
Quality Score
49 vs 84
Hardware
deepscaler:1.5b nemotron-3-super:l…
MachineMicrosoft WSLNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 5 5500Cortex-X925
Cores1220
RAM8 GB122 GB
GPUIntegrated / UnknownDevice 2e12
OSUbuntu 26.04.1 LTSUbuntu 24.04.5 LTS
Archx64arm64
Power Modeunknownperformance
Performance
deepscaler:1.5b nemotron-3-super:l…
Tokens/sec104.621.8
First chunk849 ms420 ms
TTFT850 ms2.2 s
Load time10.5 s12.4 s
Memory usage3.0 GB79.5 GB
Memory %40%65%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
nemotron-3-super:latest
Speed
23/50
TTFT
10/20
Memory
17/30
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
nemotron-3-super:latest
Reasoning
17/20
Coding
18/20
Instruction
11/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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