deepseek-r1:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Mar 5, 2026 · AMD Ryzen 9 8945HS
Global Score
66 vs 62
Hardware Fit
63 vs 91
Quality Score
67 vs 50
Hardware
deepseek-r1:7b llama3.2:1b
MachineGigabyte Technology Co., Ltd. H170M-D3HASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UV
CPUIntel Core™ i5-6500AMD Ryzen 9 8945HS
Cores416
RAM16 GB15 GB
GPUGP104 [GeForce GTX 1070]NVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
deepseek-r1:7b llama3.2:1b
Tokens/sec35.6170.2
First chunk224 ms142 ms
TTFT7.5 s142 ms
Load time7.7 s3.2 s
Memory usage4.6 GB1.6 GB
Memory %29%11%
HW Fit Score Breakdown
deepseek-r1:7b
Speed
50/50
TTFT
7/20
Memory
6/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
21/30
Quality
deepseek-r1:7b
Reasoning
16/20
Coding
10/20
Instruction
9/20
Structured
10/15
Math
14/15
Multilingual
8/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
llama3.2:1b
Reasoning
4/20
Coding
13/20
Instruction
14/20
Structured
13/15
Math
0/15
Multilingual
6/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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