deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
37 vs 79
Hardware Fit
73 vs 59
Quality Score
22 vs 87
Hardware
deepseek-r1:1.5b qwen3.6-35b-a3b
MachineLENOVO 20L7CTO1WWDocker Container
CPUIntel Core™ i5-8350UIntel Gen Intel® Core™ i9-11900H
Cores816
RAM23 GB15 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]TigerLake-H GT1 [UHD Graphics]
OSFedora Linux 43Ubuntu 26.04 LTS
Archx64x64
Power Modelow-powerperformance
Performance
deepseek-r1:1.5b qwen3.6-35b-a3b
Tokens/sec18.49.3
First chunk593 ms21 ms
TTFT30.0 s3.6 s
Load time3.8 s32.0 s
Memory usage1.0 GB1.8 GB
Memory %4%12%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
qwen3.6-35b-a3b
Speed
17/50
TTFT
12/20
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
qwen3.6-35b-a3b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
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