deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3-vl:30b
OLLAMA GGUFqwen3vlmoe · 31.1B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
37 vs 80
Hardware Fit
73 vs 98
Quality Score
22 vs 72
Hardware
deepseek-r1:1.5b qwen3-vl:30b
MachineLENOVO 20L7CTO1WWASUS
CPUIntel Core™ i5-8350UIntel Core™ Ultra 9 285K
Cores824
RAM23 GB47 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSFedora Linux 43Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b qwen3-vl:30b
Tokens/sec18.4208.9
First chunk593 ms102 ms
TTFT30.0 s684 ms
Load time3.8 s0.1 s
Memory usage1.0 GB22.0 GB
Memory %4%47%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
qwen3-vl:30b
Speed
50/50
TTFT
20/20
Memory
28/30
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-vl:30b
Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak 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