deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3.6-27b-mtp-pi-reasoning
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
37 vs 85
Hardware Fit
73 vs 80
Quality Score
22 vs 87
Hardware
deepseek-r1:1.5b qwen3.6-27b-mtp-pi…
MachineLENOVO 20L7CTO1WWASUS
CPUIntel Core™ i5-8350UAMD Ryzen 7 7800X3D 8-Core Processor
Cores816
RAM23 GB31 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA GeForce RTX 4090, Raphael
OSFedora Linux 43cachyos rolling
Archx64x64
Power Modelow-powerperformance
Performance
deepseek-r1:1.5b qwen3.6-27b-mtp-pi…
Tokens/sec18.438.8
First chunk593 ms17 ms
TTFT30.0 s432 ms
Load time3.8 sN/A
Memory usage1.0 GB24.6 GB
Memory %4%81%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
qwen3.6-27b-mtp-pi-reas…
Speed
50/50
TTFT
20/20
Memory
10/30
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
qwen3.6-27b-mtp-pi-reas…
Reasoning
16/20
Coding
18/20
Instruction
16/20
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