smollm2:1.7b
OLLAMA GGUFllama · 1.7B · Q8_0
Mar 2, 2026 · Apple M4
llama4:scout
OLLAMA GGUFllama4 · 108.6B · Q4_K_M
Oct 3, 2026 · Cortex-X925
Global Score
64 vs 81
Hardware Fit
100 vs 64
Quality Score
49 vs 88
Hardware
smollm2:1.7b llama4:scout
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.5 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
smollm2:1.7b llama4:scout
Tokens/sec51.819.6
First chunkN/A677 ms
TTFT84 ms677 ms
Load time0.4 s13.1 s
Memory usage3.7 GB63.4 GB
Memory %12%52%
HW Fit Score Breakdown
smollm2:1.7b
Speed
40/50
TTFT
30/20
Memory
30/30
llama4:scout
Speed
20/50
TTFT
20/20
Memory
24/30
Quality
smollm2:1.7b
Reasoning
7/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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
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