deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score

47 vs 66

Hardware Fit

51 vs 40

Quality Score

45 vs 77

Hardware

deepseek-r1:70b gemma4:31b

MachineNVIDIA NVIDIA_DGX_SparkASUSTeK COMPUTER INC. GX10

CPUCortex-X925Cortex-X925

Cores2020

RAM122 GB122 GB

GPUDevice 2e12Device 2e12

OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS

Archarm64arm64

Power Modeperformanceperformance

Performance

deepseek-r1:70b gemma4:31b

Tokens/sec4.710.7

First chunk557 ms983 ms

TTFT557 ms20.3 s

Load time52.6 s8.8 s

Memory usage49.5 GB21.4 GB

Memory %41%18%

HW Fit Score Breakdown

deepseek-r1:70b

Speed

4/50

TTFT

20/20

Memory

27/30

gemma4:31b

Speed

10/50

TTFT

0/20

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

gemma4:31b

Reasoning

14/20

Coding

17/20

Instruction

13/20

Structured

14/15

Math

10/15

Multilingual

9/10

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

View deepseek-r1:70b details | View gemma4:31b 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