qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 10, 2026 · Apple M4

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score

66 vs 69

Hardware Fit

34 vs 50

Quality Score

80 vs 77

Hardware

qwen3.5:27b mistralai/devstral…

MachineMac miniMacBook Air

CPUApple M4Apple M4

Cores1010

RAM24 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:27b mistralai/devstral…

Tokens/sec4.05.7

First chunk1655 ms5007 ms

TTFT1.7 s5.0 s

Load time12.9 sN/A

Memory usage21.3 GB13.2 GB

Memory %89%41%

HW Fit Score Breakdown

qwen3.5:27b

Speed

8/50

TTFT

20/20

Memory

6/30

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

Quality

qwen3.5:27b

Reasoning

16/20

Coding

18/20

Instruction

9/20

Structured

15/15

Math

12/15

Multilingual

10/10

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

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

View qwen3.5:27b details | View mistralai/devstral… 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