mlx-community/meta-llama-3.1-8b-instruct

LM-STUDIO MLX

llama · 8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score

77 vs 47

Hardware Fit

100 vs 51

Quality Score

67 vs 45

Hardware

mlx-community/meta… deepseek-r1:70b

MachineMac miniNVIDIA NVIDIA_DGX_Spark

CPUApple M4 ProCortex-X925

Cores1420

RAM64 GB122 GB

GPUApple M4 ProDevice 2e12

OSmacOS 15.7.4Ubuntu 24.04.4 LTS

Archarm64arm64

Power Modebalancedperformance

Performance

mlx-community/meta… deepseek-r1:70b

Tokens/sec54.34.7

First chunk277 ms557 ms

TTFT277 ms557 ms

Load timeN/A52.6 s

Memory usage4.2 GB49.5 GB

Memory %7%41%

HW Fit Score Breakdown

mlx-community/meta-llam…

Speed

50/50

TTFT

20/20

Memory

30/30

deepseek-r1:70b

Speed

4/50

TTFT

20/20

Memory

27/30

Quality

mlx-community/meta-llam…

Reasoning

11/20

Coding

14/20

Instruction

14/20

Structured

15/15

Math

4/15

Multilingual

9/10

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

deepseek-r1:70b

Reasoning

3/20

Coding

1/20

Instruction

14/20

Structured

9/15

Math

8/15

Multilingual

10/10

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

View mlx-community/meta… details | View deepseek-r1:70b 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