qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 4bit
Mar 6, 2026 · Apple M4 Pro
mlx-community/Yi-1.5-6B-Chat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
53 vs 73
Hardware Fit
89 vs 100
Quality Score
38 vs 62
Hardware
qwen3.5-0.8b-mlx mlx-community/Yi-1…
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-0.8b-mlx mlx-community/Yi-1…
Tokens/sec52.929.1
First chunk4013 ms451 ms
TTFT4.0 s451 ms
Load timeN/AN/A
Memory usage0.6 GB0.9 GB
Memory %1%3%
HW Fit Score Breakdown
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
9/20
Memory
30/30
mlx-community/Yi-1.5-6B…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5-0.8b-mlx
Reasoning
7/20
Coding
2/20
Instruction
12/20
Structured
10/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
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
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