deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Qwen3-80B:80B
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
37 vs 82
Hardware Fit
73 vs 59
Quality Score
22 vs 92
Hardware
deepseek-r1:1.5b Qwen3-80B:80B
MachineLENOVO 20L7CTO1WWGMKtec NucBox EVO-T2S
CPUIntel Core™ i5-8350UIntel Core™ Ultra X7 358H
Cores816
RAM23 GB64 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Intel(R) Arc(TM) B390 GPU
OSFedora Linux 43Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b Qwen3-80B:80B
Tokens/sec18.419.6
First chunk593 ms823 ms
TTFT30.0 s823 ms
Load time3.8 s41.6 s
Memory usage1.0 GB46.9 GB
Memory %4%74%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
Qwen3-80B:80B
Speed
26/50
TTFT
20/20
Memory
13/30
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
Qwen3-80B:80B
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
15/15
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