codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score

67 vs 71

Hardware Fit

67 vs 88

Quality Score

67 vs 63

Hardware

codestral:22b qwen3.5-4b-mlx

MachineNVIDIA NVIDIA_DGX_SparkMacBook Air

CPUCortex-X925Apple M4

Cores2010

RAM122 GB32 GB

GPUDevice 2e12Apple M4

OSUbuntu 24.04.4 LTSmacOS 26.3

Archarm64arm64

Power Modeperformancebalanced

Performance

codestral:22b qwen3.5-4b-mlx

Tokens/sec17.223.1

First chunk129 ms3279 ms

TTFT129 ms3.3 s

Load time11.6 sN/A

Memory usage18.9 GB2.9 GB

Memory %16%9%

HW Fit Score Breakdown

codestral:22b

Speed

17/50

TTFT

20/20

Memory

30/30

qwen3.5-4b-mlx

Speed

45/50

TTFT

13/20

Memory

30/30

Quality

codestral:22b

Reasoning

11/20

Coding

17/20

Instruction

9/20

Structured

14/15

Math

6/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.5-4b-mlx

Reasoning

15/20

Coding

16/20

Instruction

6/20

Structured

6/15

Math

11/15

Multilingual

9/10

Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

View codestral:22b details | View qwen3.5-4b-mlx details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest