mlx-community/Yi-1.5-6B-Chat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
deepseek-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
73 vs 69
Hardware Fit
100 vs 100
Quality Score
62 vs 55
Hardware
mlx-community/Yi-1… deepseek-v2:16b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/Yi-1… deepseek-v2:16b
Tokens/sec29.156.6
First chunk451 msN/A
TTFT451 ms239 ms
Load timeN/A1.2 s
Memory usage0.9 GB17.7 GB
Memory %3%55%
HW Fit Score Breakdown
mlx-community/Yi-1.5-6B…
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-v2:16b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
mlx-community/Yi-1.5-6B…
Reasoning
10/20
Coding
11/20
Instruction
13/20
Structured
13/15
Math
9/15
Multilingual
6/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Adequate
deepseek-v2:16b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
10/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate 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