deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score

47 vs 85

Hardware Fit

51 vs 64

Quality Score

45 vs 94

Hardware

deepseek-r1:70b gemma-4-31b-it-mlx

MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro

CPUCortex-X925Apple M4 Max

Cores2016

RAM122 GB128 GB

GPUDevice 2e12Apple M4 Max

OSUbuntu 24.04.4 LTSmacOS 26.5.2

Archarm64arm64

Power Modeperformancebalanced

Performance

deepseek-r1:70b gemma-4-31b-it-mlx

Tokens/sec4.713.6

First chunk557 ms16 ms

TTFT557 ms558 ms

Load time52.6 s12.3 s

Memory usage49.5 GB0.0 GB

Memory %41%0%

HW Fit Score Breakdown

deepseek-r1:70b

Speed

4/50

TTFT

20/20

Memory

27/30

gemma-4-31b-it-mlx

Speed

14/50

TTFT

20/20

Memory

30/30

Quality

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

gemma-4-31b-it-mlx

Reasoning

19/20

Coding

19/20

Instruction

18/20

Structured

15/15

Math

14/15

Multilingual

9/10

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

View deepseek-r1:70b details | View gemma-4-31b-it-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