qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 24, 2026 · Apple M2
qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex
LM-STUDIO GGUFqwen35moe · 35B
Aug 19, 2026 · Apple M4 Max
Global Score
53 vs 90
Hardware Fit
81 vs 100
Quality Score
41 vs 86
Hardware
qwen3.5:4b-mlx qwen3.6-35b-a3b-cl…
MachineMac miniMacBook Pro
CPUApple M2Apple M4 Max
Cores816
RAM8 GB128 GB
GPUApple M2Apple M4 Max
OSmacOS 26.5.2macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:4b-mlx qwen3.6-35b-a3b-cl…
Tokens/sec24.878.1
First chunk317 ms7 ms
TTFT7.4 s138 ms
Load time0.0 sN/A
Memory usage3.9 GB23.9 GB
Memory %49%19%
HW Fit Score Breakdown
qwen3.5:4b-mlx
Speed
50/50
TTFT
6/20
Memory
25/30
qwen3.6-35b-a3b-claude-…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:4b-mlx
Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong
qwen3.6-35b-a3b-claude-…
Reasoning
18/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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