Tokenstead - Find the right AI model for your hardware

Orin Nano 8 8GB

17 models / sorted by best_quality

Quality Fastest Least mem Newest

Model Fit Speed Memory Scores / Run

Runs comfortably

Ornith-1.5-9B Q4_K_M

5.8GB 262k ctx

Runs comfortably

6 tok/s

ⓘ estimated

6 / 8GB

78 / 76 / 74

FIT Runs comfortably

SPEED 6 tok/s

ⓘ estimated

MEMORY 6/8GB

Qwen3 8B Q4_K_M

5.2GB 128k ctx

Runs comfortably

7 tok/s

ⓘ estimated

5 / 8GB

67 / 70 / 65

FIT Runs comfortably

SPEED 7 tok/s

ⓘ estimated

MEMORY 5/8GB

Qwen3 4B Q4_K_M

2.6GB 32k ctx

Runs comfortably

14 tok/s

ⓘ estimated

3 / 8GB

58 / 60 / 56

FIT Runs comfortably

SPEED 14 tok/s

ⓘ estimated

MEMORY 3/8GB

Phi-4 Mini Q4_K_M

2.5GB 128k ctx

Runs comfortably

15 tok/s

ⓘ estimated

3 / 8GB

55 / 58 / 52

FIT Runs comfortably

SPEED 15 tok/s

ⓘ estimated

MEMORY 3/8GB

Phi-4 Mini Q8_0

4.1GB 128k ctx

Runs comfortably

9 tok/s

ⓘ estimated

4 / 8GB

55 / 58 / 52

FIT Runs comfortably

SPEED 9 tok/s

ⓘ estimated

MEMORY 4/8GB

Llama 3.1 8B Instruct Q4_K_M

4.5GB 128k ctx

Runs comfortably

8 tok/s

ⓘ estimated

5 / 8GB

52 / 55 / 62

FIT Runs comfortably

SPEED 8 tok/s

ⓘ estimated

MEMORY 5/8GB

Gemma 3 4B Q8_0

5.0GB 128k ctx

Runs comfortably

7 tok/s

ⓘ estimated

5 / 8GB

42 / 45 / 55

FIT Runs comfortably

SPEED 7 tok/s

ⓘ estimated

MEMORY 5/8GB

Gemma 3 4B Q4_K_M

3.0GB 128k ctx

Runs comfortably

12 tok/s

ⓘ estimated

3 / 8GB

42 / 45 / 55

FIT Runs comfortably

SPEED 12 tok/s

ⓘ estimated

MEMORY 3/8GB

Llama 3.2 3B Instruct Q4_K_M

2.0GB 128k ctx

Runs comfortably

19 tok/s

ⓘ estimated

2 / 8GB

35 / 38 / 50

FIT Runs comfortably

SPEED 19 tok/s

ⓘ estimated

MEMORY 2/8GB

Llama 3.2 3B Instruct Q8_0

3.5GB 128k ctx

Runs comfortably

11 tok/s

ⓘ estimated

4 / 8GB

35 / 38 / 50

FIT Runs comfortably

SPEED 11 tok/s

ⓘ estimated

MEMORY 4/8GB

Runs tight

Qwen3.8-27B UD-IQ1_S Unsloth

6.2GB 0k cap

Runs tight

6 tok/s

ⓘ estimated

6 / 8GB

88 / 89 / 85

FIT Runs tight

SPEED 6 tok/s

ⓘ estimated

MEMORY 6/8GB

Ornith-1.5-9B Q5_K_M

6.6GB 262k ctx

Runs tight

6 tok/s

ⓘ estimated

7 / 8GB

78 / 76 / 74

FIT Runs tight

SPEED 6 tok/s

ⓘ estimated

MEMORY 7/8GB

Ornith-1.5-9B Q6_K

7.6GB 0k cap

Runs tight

5 tok/s

ⓘ estimated

8 / 8GB

78 / 76 / 74

FIT Runs tight

SPEED 5 tok/s

ⓘ estimated

MEMORY 8/8GB

Gemma 4 12B Q4_K_M

7.2GB 128k ctx

Runs tight

5 tok/s

ⓘ estimated

7 / 8GB

70 / 74 / 72

FIT Runs tight

SPEED 5 tok/s

ⓘ estimated

MEMORY 7/8GB

Gemma 3 12B Q4_K_M

7.5GB 128k ctx

Runs tight

5 tok/s

ⓘ estimated

8 / 8GB

62 / 65 / 68

FIT Runs tight

SPEED 5 tok/s

ⓘ estimated

MEMORY 8/8GB

Mistral Nemo 12B Q4_K_M

7.3GB 128k ctx

Runs tight

5 tok/s

ⓘ estimated

7 / 8GB

58 / 60 / 62

FIT Runs tight

SPEED 5 tok/s

ⓘ estimated

MEMORY 7/8GB

Llama 3.1 8B Instruct Q8_0

8.0GB 0k cap

Runs tight

5 tok/s

ⓘ estimated

8 / 8GB

52 / 55 / 62

FIT Runs tight

SPEED 5 tok/s

ⓘ estimated

MEMORY 8/8GB

Coding alternatives

Hosted coding assistants for comparison - per seat

Cursor Hobby

AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...

$0.0

/MONTH

GitHub Copilot Individual

AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...

$10.0

/MONTH

GitHub Copilot Business

AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...

$19.0

/MONTH

Cursor Pro

AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...

$20.0

/MONTH

GitHub Copilot Enterprise

AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...

$39.0

/MONTH

Cursor Business

AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...

$40.0

/MONTH

Per-token monthly figures are estimates at typical usage. Prices verified periodically - always confirm current pricing on the provider's website.

On a monthly budget? Compare owning hardware vs renting cloud →