deepseek-r1:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score

47 vs 57

Hardware Fit

51 vs 61

Quality Score

45 vs 55

Hardware

deepseek-r1:70b qwen3.5:9b

MachineNVIDIA NVIDIA_DGX_SparkAZW GTR Pro

CPUCortex-X925AMD RYZEN AI MAX+ 395

Cores2032

RAM122 GB125 GB

GPUDevice 2e12AMD Radeon 8060S

OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS

Archarm64x64

Power Modeperformancelow-power

Performance

deepseek-r1:70b qwen3.5:9b

Tokens/sec4.730.3

First chunk557 ms205 ms

TTFT557 ms8.7 s

Load time52.6 s5.6 s

Memory usage49.5 GB18.8 GB

Memory %41%15%

HW Fit Score Breakdown

deepseek-r1:70b

Speed

4/50

TTFT

20/20

Memory

27/30

qwen3.5:9b

Speed

30/50

TTFT

1/20

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

qwen3.5:9b

Reasoning

17/20

Coding

2/20

Instruction

7/20

Structured

8/15

Math

12/15

Multilingual

9/10

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

View deepseek-r1:70b details | View qwen3.5:9b 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