devstral:24b

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

Global Score

80 vs 70

Hardware Fit

79 vs 93

Quality Score

80 vs 60

Hardware

devstral:24b qwen3.5-2b-mlx

MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4MacBook Air

CPUIntel Core™ i5-14400FApple M4

Cores1610

RAM32 GB32 GB

GPUNVIDIA GeForce RTX 5060 TiApple M4

OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

devstral:24b qwen3.5-2b-mlx

Tokens/sec20.232.9

First chunk137 ms3096 ms

TTFT137 ms3.1 s

Load time9.6 sN/A

Memory usage14.2 GB2.5 GB

Memory %45%8%

HW Fit Score Breakdown

devstral:24b

Speed

33/50

TTFT

20/20

Memory

26/30

qwen3.5-2b-mlx

Speed

50/50

TTFT

13/20

Memory

30/30

Quality

devstral:24b

Reasoning

16/20

Coding

17/20

Instruction

13/20

Structured

15/15

Math

9/15

Multilingual

10/10

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

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

View devstral:24b details | View qwen3.5-2b-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