llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
deepseek-r1:latest
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
63 vs 23
Hardware Fit
100 vs 70
Quality Score
47 vs 3
Hardware
llama3.2:1b deepseek-r1:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUCortex-A78AECortex-A78AE
Cores66
RAM7 GB7 GB
GPUIntegrated / UnknownIntegrated / Unknown
OSUbuntu 22.04.5 LTSUbuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.2:1b deepseek-r1:latest
Tokens/sec40.29.8
First chunk1087 ms1206 ms
TTFT1.1 s1.2 s
Load time6.2 s17.8 s
Memory usage1.4 GB4.8 GB
Memory %19%65%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-r1:latest
Speed
32/50
TTFT
20/20
Memory
18/30
Quality
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
deepseek-r1:latest
Reasoning
0/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
2/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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