deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
nvidia/nemotron-3-nano
LM-STUDIO MLXnemotron_h · 30B · 4bit
Mar 4, 2026 · Apple M4
Global Score
37 vs 84
Hardware Fit
73 vs 100
Quality Score
22 vs 77
Hardware
deepseek-r1:1.5b nvidia/nemotron-3-…
MachineLENOVO 20L7CTO1WWMacBook Air
CPUIntel Core™ i5-8350UApple M4
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4
OSFedora Linux 43macOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b nvidia/nemotron-3-…
Tokens/sec18.447.9
First chunk593 ms465 ms
TTFT30.0 s465 ms
Load time3.8 sN/A
Memory usage1.0 GB16.6 GB
Memory %4%52%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
nvidia/nemotron-3-nano
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
deepseek-r1:1.5b
Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak
nvidia/nemotron-3-nano
Reasoning
13/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong 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