deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
37 vs 74
Hardware Fit
73 vs 100
Quality Score
22 vs 63
Hardware
deepseek-r1:1.5b llama3.2:3b
MachineLENOVO 20L7CTO1WWMacBook Air
CPUIntel Core™ i5-8350UApple M4
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4
OSFedora Linux 43macOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b llama3.2:3b
Tokens/sec18.444.1
First chunk593 msN/A
TTFT30.0 s178 ms
Load time3.8 s0.8 s
Memory usage1.0 GB7.0 GB
Memory %4%22%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
llama3.2:3b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
deepseek-r1:1.5b
Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak
llama3.2:3b
Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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