qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 24, 2026 · Apple M2
codestral:latest
OLLAMA GGUFllama · 22.2B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
53 vs 76
Hardware Fit
82 vs 91
Quality Score
41 vs 69
Hardware
qwen3.5:4b-mlx codestral:latest
MachineMac miniGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M2Intel Core™ i5-14400F
Cores816
RAM8 GB32 GB
GPUApple M2NVIDIA GeForce RTX 5060 Ti
OSmacOS 26.5.2Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5:4b-mlx codestral:latest
Tokens/sec24.727.4
First chunk302 ms86 ms
TTFT7.4 s86 ms
Load time3.2 s7.2 s
Memory usage3.8 GB12.6 GB
Memory %47%40%
HW Fit Score Breakdown
qwen3.5:4b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
codestral:latest
Speed
43/50
TTFT
20/20
Memory
28/30
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
codestral:latest
Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
13/15
Math
7/15
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