deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score

47 vs 29

Hardware Fit

51 vs 86

Quality Score

45 vs 4

Hardware

deepseek-r1:70b qwen3:4b

MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUCortex-X925Cortex-A78AE

Cores206

RAM122 GB7 GB

GPUDevice 2e12Integrated / Unknown

OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS

Archarm64arm64

Power Modeperformancebalanced

Performance

deepseek-r1:70b qwen3:4b

Tokens/sec4.717.9

First chunk557 ms1010 ms

TTFT557 ms6.4 s

Load time52.6 s9.5 s

Memory usage49.5 GB3.0 GB

Memory %41%40%

HW Fit Score Breakdown

deepseek-r1:70b

Speed

4/50

TTFT

20/20

Memory

27/30

qwen3:4b

Speed

50/50

TTFT

8/20

Memory

28/30

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

qwen3:4b

Reasoning

4/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

0/15

Multilingual

0/10

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

View deepseek-r1:70b details | View qwen3:4b 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