qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

mlx-community/Llama-3.2-1B-Instruct-4bit

LM-STUDIO GGUF

Marginal

Mar 5, 2026 · Apple M4

Global Score

20 vs 57

Hardware Fit

37 vs 100

Quality Score

12 vs 39

Hardware

qwen3.5:27b mlx-community/Llam…

MachineAZW GTR ProMacBook Air

CPUAMD RYZEN AI MAX+ 395Apple M4

Cores3210

RAM125 GB32 GB

GPUAMD Radeon 8060SApple M4

OSUbuntu 24.04.4 LTSmacOS 26.3

Archx64arm64

Power Modelow-powerbalanced

Performance

qwen3.5:27b mlx-community/Llam…

Tokens/sec10.6126.4

First chunk358 ms139 ms

TTFT13.7 s139 ms

Load time10.8 sN/A

Memory usage39.7 GB0.3 GB

Memory %32%1%

HW Fit Score Breakdown

qwen3.5:27b

Speed

9/50

TTFT

0/20

Memory

28/30

mlx-community/Llama-3.2…

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

qwen3.5:27b

Reasoning

2/20

Coding

0/20

Instruction

2/20

Structured

0/15

Math

0/15

Multilingual

8/10

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

mlx-community/Llama-3.2…

Reasoning

5/20

Coding

3/20

Instruction

15/20

Structured

10/15

Math

1/15

Multilingual

5/10

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

View qwen3.5:27b details | View mlx-community/Llam… 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