deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Sage-A1.5-Q4_K_M-GGUF:latest
OLLAMA GGUFqwen35moe · 35.5B · Q4_K_M
Oct 23, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
37 vs 86
Hardware Fit
73 vs 86
Quality Score
22 vs 86
Hardware
deepseek-r1:1.5b Sage-A1.5-Q4_K_M-G…
MachineLENOVO 20L7CTO1WWMicro-Star International Co., Ltd. MS-7E51
CPUIntel Core™ i5-8350UAMD Ryzen 7 9700X 8-Core Processor
Cores816
RAM23 GB31 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSFedora Linux 43Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b Sage-A1.5-Q4_K_M-G…
Tokens/sec18.475.2
First chunk593 ms168 ms
TTFT30.0 s168 ms
Load time3.8 s0.0 s
Memory usage1.0 GB21.4 GB
Memory %4%69%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
Sage-A1.5-Q4_K_M-GGUF:l…
Speed
50/50
TTFT
20/20
Memory
16/30
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
Sage-A1.5-Q4_K_M-GGUF:l…
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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