deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
glm4:9b
OLLAMA GGUFchatglm · 9.4B · Q4_0
Mar 6, 2026 · Apple M4
Global Score
37 vs 76
Hardware Fit
73 vs 88
Quality Score
22 vs 71
Hardware
deepseek-r1:1.5b glm4:9b
MachineLENOVO 20L7CTO1WWMacBook Air
CPUIntel Core™ i5-8350UApple M4
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4
OSFedora Linux 43macOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b glm4:9b
Tokens/sec18.419.0
First chunk593 ms290 ms
TTFT30.0 s290 ms
Load time3.8 s0.8 s
Memory usage1.0 GB8.1 GB
Memory %4%25%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
glm4:9b
Speed
38/50
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
glm4:9b
Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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