deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
Global Score
37 vs 34
Hardware Fit
73 vs 58
Quality Score
22 vs 23
Hardware
deepseek-r1:1.5b qwen3.5:latest
MachineLENOVO 20L7CTO1WWMac mini
CPUIntel Core™ i5-8350UApple M4
Cores810
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4
OSFedora Linux 43macOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b qwen3.5:latest
Tokens/sec18.413.3
First chunk593 ms438 ms
TTFT30.0 s19.8 s
Load time3.8 s0.2 s
Memory usage1.0 GB8.0 GB
Memory %4%50%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
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
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor 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