deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
llama3:latest
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
64 vs 71
Hardware Fit
98 vs 95
Quality Score
49 vs 60
Hardware
deepscaler:1.5b llama3:latest
MachineMicrosoft WSLMacBook Air
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM8 GB32 GB
GPUIntegrated / UnknownApple M4
OSUbuntu 26.04.1 LTSmacOS 26.3
Archx64arm64
Power Modeunknownbalanced
Performance
deepscaler:1.5b llama3:latest
Tokens/sec104.622.3
First chunk849 msN/A
TTFT850 ms295 ms
Load time10.5 s0.8 s
Memory usage3.0 GB5.6 GB
Memory %40%18%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
llama3:latest
Speed
35/50
TTFT
30/20
Memory
30/30
Quality
deepscaler:1.5b
Reasoning
10/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
11/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Weak
llama3:latest
Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak 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