qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
70 vs 76
Hardware Fit
93 vs 89
Quality Score
60 vs 71
Hardware
qwen3.5-2b-mlx ministral-3:8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-2b-mlx ministral-3:8b
Tokens/sec32.919.5
First chunk3096 ms328 ms
TTFT3.1 s328 ms
Load timeN/A1.5 s
Memory usage2.5 GB10.6 GB
Memory %8%33%
HW Fit Score Breakdown
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
ministral-3:8b
Speed
39/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
6/15
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