deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score

47 vs 18

Hardware Fit

51 vs 53

Quality Score

45 vs 3

Hardware

deepseek-r1:70b qwen3.5:0.8b

MachineNVIDIA NVIDIA_DGX_SparkLENOVO 20L7CTO1WW

CPUCortex-X925Intel Core™ i5-8350U

Cores208

RAM122 GB23 GB

GPUDevice 2e12Kaby Lake-R GT2 [UHD Graphics 620]

OSUbuntu 24.04.4 LTSFedora Linux 43

Archarm64x64

Power Modeperformancelow-power

Performance

deepseek-r1:70b qwen3.5:0.8b

Tokens/sec4.79.4

First chunk557 ms799 ms

TTFT557 ms30.0 s

Load time52.6 s3.3 s

Memory usage49.5 GB1.9 GB

Memory %41%8%

HW Fit Score Breakdown

deepseek-r1:70b

Speed

4/50

TTFT

20/20

Memory

27/30

qwen3.5:0.8b

Speed

23/50

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

qwen3.5:0.8b

Reasoning

0/20

Coding

0/20

Instruction

2/20

Structured

0/15

Math

0/15

Multilingual

1/10

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

View deepseek-r1:70b details | View qwen3.5:0.8b 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