deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Oct 20, 2026 · Apple M1 Pro
Global Score
37 vs 78
Hardware Fit
73 vs 56
Quality Score
22 vs 87
Hardware
deepseek-r1:1.5b qwen3.8-27b-mlx
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M1 Pro
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Pro
OSFedora Linux 43macOS 15.6.1
Archx64arm64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b qwen3.8-27b-mlx
Tokens/sec18.410.8
First chunk593 ms8 ms
TTFT30.0 s2.6 s
Load time3.8 sN/A
Memory usage1.0 GB21.0 GB
Memory %4%66%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
16/20
Memory
17/30
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
qwen3.8-27b-mlx
Reasoning
18/20
Coding
18/20
Instruction
15/20
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