deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
37 vs 67
Hardware Fit
73 vs 67
Quality Score
22 vs 67
Hardware
deepseek-r1:1.5b codestral:22b
MachineLENOVO 20L7CTO1WWNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i5-8350UCortex-X925
Cores820
RAM23 GB122 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Device 2e12
OSFedora Linux 43Ubuntu 24.04.4 LTS
Archx64arm64
Power Modelow-powerperformance
Performance
deepseek-r1:1.5b codestral:22b
Tokens/sec18.417.2
First chunk593 ms129 ms
TTFT30.0 s129 ms
Load time3.8 s11.6 s
Memory usage1.0 GB18.9 GB
Memory %4%16%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
codestral:22b
Speed
17/50
TTFT
20/20
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
codestral:22b
Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak 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