deepseek-r1-distill-qwen-14b-mlx

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score

36 vs 88

Hardware Fit

53 vs 85

Quality Score

28 vs 89

Hardware

deepseek-r1-distil… huihui-qwen3.6-35b…

MachineMac miniGigabyte Technology Co., Ltd. B550M AORUS PRO

CPUApple M4AMD Ryzen 5 5600X 6-Core Processor

Cores1012

RAM24 GB47 GB

GPUApple M4AD106 [GeForce RTX 4060 Ti]

OSmacOS 26.3cachyos rolling

Archarm64x64

Power Modebalancedlow-power

Performance

deepseek-r1-distil… huihui-qwen3.6-35b…

Tokens/sec10.337.7

First chunk27 ms18 ms

TTFT20.7 s2.9 s

Load time15.4 sN/A

Memory usage1.0 GB26.1 GB

Memory %4%56%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

huihui-qwen3.6-35b-a3b-…

Speed

50/50

TTFT

13/20

Memory

22/30

Quality

deepseek-r1-distill-qwe…

Reasoning

3/20

Coding

6/20

Instruction

6/20

Structured

3/15

Math

2/15

Multilingual

8/10

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

huihui-qwen3.6-35b-a3b-…

Reasoning

19/20

Coding

15/20

Instruction

15/20

Structured

15/15

Math

15/15

Multilingual

10/10

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

View deepseek-r1-distil… details | View huihui-qwen3.6-35b… 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