deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
37 vs 88
Hardware Fit
73 vs 94
Quality Score
22 vs 85
Hardware
deepseek-r1:1.5b huihui-qwen3.6-35b…
MachineLENOVO 20L7CTO1WWGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-8350UAMD Ryzen 5 5600X 6-Core Processor
Cores812
RAM23 GB47 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]AD106 [GeForce RTX 4060 Ti]
OSFedora Linux 43cachyos rolling
Archx64x64
Power Modelow-powerlow-power
Performance
deepseek-r1:1.5b huihui-qwen3.6-35b…
Tokens/sec18.439.8
First chunk593 ms3 ms
TTFT30.0 s479 ms
Load time3.8 sN/A
Memory usage1.0 GB24.4 GB
Memory %4%52%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
20/20
Memory
24/30
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
huihui-qwen3.6-35b-a3b-…
Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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