llama4:scout
OLLAMA GGUFllama4 · 108.6B · Q4_K_M
Oct 3, 2026 · Cortex-X925
qwen2.5-coder:3b
OLLAMA GGUFqwen2 · 3.1B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
81 vs 73
Hardware Fit
64 vs 100
Quality Score
88 vs 61
Hardware
llama4:scout qwen2.5-coder:3b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUCortex-X925Cortex-A78AE
Cores206
RAM122 GB7 GB
GPUDevice 2e12Integrated / Unknown
OSUbuntu 24.04.5 LTSUbuntu 22.04.5 LTS
Archarm64arm64
Power Modeperformancebalanced
Performance
llama4:scout qwen2.5-coder:3b
Tokens/sec19.621.3
First chunk677 ms969 ms
TTFT677 ms969 ms
Load time13.1 s6.6 s
Memory usage63.4 GB2.0 GB
Memory %52%27%
HW Fit Score Breakdown
llama4:scout
Speed
20/50
TTFT
20/20
Memory
24/30
qwen2.5-coder:3b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama4:scout
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
13/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen2.5-coder:3b
Reasoning
8/20
Coding
15/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate 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