llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Core™ i9-14900K
Global Score
74 vs 83
Hardware Fit
99 vs 70
Quality Score
63 vs 89
Hardware
llama3.2:3b qwen3:30b-a3b-inst…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMicro-Star International Co., Ltd. MS-7D98
CPUCortex-A78AEIntel Core™ i9-14900K
Cores632
RAM7 GB128 GB
GPUIntegrated / UnknownIntel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:3b qwen3:30b-a3b-inst…
Tokens/sec21.121.2
First chunk1032 ms468 ms
TTFT1.0 s468 ms
Load time8.4 s9.6 s
Memory usage2.4 GB17.7 GB
Memory %32%14%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3:30b-a3b-instruct-…
Speed
20/50
TTFT
20/20
Memory
30/30
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
qwen3:30b-a3b-instruct-…
Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
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