deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score

47 vs 65

Hardware Fit

51 vs 88

Quality Score

45 vs 55

Hardware

deepseek-r1:70b qwen3.5-2b-mlx

MachineNVIDIA NVIDIA_DGX_SparkMac mini

CPUCortex-X925Apple M4 Pro

Cores2014

RAM122 GB64 GB

GPUDevice 2e12Apple M4 Pro

OSUbuntu 24.04.4 LTSmacOS 15.7.4

Archarm64arm64

Power Modeperformancebalanced

Performance

deepseek-r1:70b qwen3.5-2b-mlx

Tokens/sec4.748.9

First chunk557 ms4208 ms

TTFT557 ms4.2 s

Load time52.6 sN/A

Memory usage49.5 GB1.6 GB

Memory %41%3%

HW Fit Score Breakdown

deepseek-r1:70b

Speed

4/50

TTFT

20/20

Memory

27/30

qwen3.5-2b-mlx

Speed

50/50

TTFT

8/20

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

qwen3.5-2b-mlx

Reasoning

10/20

Coding

7/20

Instruction

13/20

Structured

14/15

Math

3/15

Multilingual

8/10

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

View deepseek-r1:70b details | View qwen3.5-2b-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