llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
63 vs 61
Hardware Fit
100 vs 85
Quality Score
47 vs 51
Hardware
llama3.2:1b qwen3:0.6b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperLENOVO 20L7CTO1WW
CPUCortex-A78AEIntel Core™ i5-8350U
Cores68
RAM7 GB23 GB
GPUIntegrated / UnknownKaby Lake-R GT2 [UHD Graphics 620]
OSUbuntu 22.04.5 LTSFedora Linux 43
Archarm64x64
Power Modebalancedlow-power
Performance
llama3.2:1b qwen3:0.6b
Tokens/sec40.227.0
First chunk1087 ms597 ms
TTFT1.1 s8.7 s
Load time6.2 s1.8 s
Memory usage1.4 GB0.9 GB
Memory %19%4%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
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
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
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