llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
74 vs 81
Hardware Fit
99 vs 80
Quality Score
63 vs 81
Hardware
llama3.2:3b devstral-small-2-2…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperSystem manufacturer
CPUCortex-A78AEAMD Ryzen 7 5800X 8-Core Processor
Cores616
RAM7 GB31 GB
GPUIntegrated / UnknownNavi 44 [Radeon RX 9060 XT]
OSUbuntu 22.04.5 LTSUbuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance
Performance
llama3.2:3b devstral-small-2-2…
Tokens/sec21.121.5
First chunk1032 ms12 ms
TTFT1.0 s212 ms
Load time8.4 sN/A
Memory usage2.4 GB15.9 GB
Memory %32%51%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
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
devstral-small-2-24b-in…
Reasoning
16/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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