llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Global Score
74 vs 90
Hardware Fit
99 vs 96
Quality Score
63 vs 88
Hardware
llama3.2:3b Kimi-48B:48B
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUCortex-A78AENVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores620
RAM7 GB55 GB
GPUIntegrated / UnknownNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.2:3b Kimi-48B:48B
Tokens/sec21.162.7
First chunk1032 ms397 ms
TTFT1.0 s397 ms
Load time8.4 s16.8 s
Memory usage2.4 GB25.5 GB
Memory %32%47%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
llama3.2:3b
Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
Kimi-48B:48B
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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