qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
61 vs 63
Hardware Fit
85 vs 100
Quality Score
51 vs 47
Hardware
qwen3:0.6b llama3.2:1b
MachineLENOVO 20L7CTO1WWNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i5-8350UCortex-A78AE
Cores86
RAM23 GB7 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Integrated / Unknown
OSFedora Linux 43Ubuntu 22.04.5 LTS
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3:0.6b llama3.2:1b
Tokens/sec27.040.2
First chunk597 ms1087 ms
TTFT8.7 s1.1 s
Load time1.8 s6.2 s
Memory usage0.9 GB1.4 GB
Memory %4%19%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
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
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
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