COMPARE.

microsoft

Dayhoff-170M-UR90-HL-6000

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

0.32 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

Dayhoff-3b-GR-HM-11000

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

5.56 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

Dayhoff-3b-GR-HM-c

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

11.11 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

Dayhoff-3b-UR90

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

11.11 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

Dayhoff-3b-UR90-10

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

5.56 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

Dayhoff-3b-UR90-10000

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

5.56 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

Dayhoff-3b-UR90-20350

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

5.56 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

Dayhoff-3b-UR90-30000

Models

Context window

262,144 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

5.56 GiB

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/allenai/olmOCR-7B-0725-FP8

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/meta-llama/Llama-Guard-3-8B

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/meta-llama/Llama-Guard-4-12B

Models^*

Maximum output

163,840 tokens^*

Maximum input

163,840 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/microsoft/WizardLM-2-8x22B

Models^*

Maximum output

65,536 tokens^*

Maximum input

65,536 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/NousResearch/Hermes-3-Llama-3.1-70B

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/Qwen/Qwen2.5-7B-Instruct

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/Sao10K/L3.1-70B-Euryale-v2.2

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

deepinfra/Sao10K/L3.3-70B-Euryale-v2.3

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Tool choice

No^*

Radar · unrated0/4 core tests · not enough evidence

deepseek

DeepSeek-Coder-V2-Base

Models

Context window

163,840 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

439.10 GiB

Radar · unrated0/4 core tests · not enough evidence

deepseek

DeepSeek-Coder-V2-Instruct

Models

Context window

163,840 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

439.10 GiB

Radar · unrated0/4 core tests · not enough evidence

deepseek

DeepSeek-Coder-V2-Instruct-0724

Models

Context window

163,840 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

439.10 GiB

Radar · unrated0/4 core tests · not enough evidence

deepseek

DeepSeek-Coder-V2-Lite-Base

Models

Context window

163,840 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

29.26 GiB

Radar · unrated0/4 core tests · not enough evidence

deepseek

DeepSeek-Coder-V2-Lite-Instruct

Models

Context window

163,840 tokens

Open weights

Yes

Model license

other

Checkpoint tensor payload

29.26 GiB

Radar · unrated0/4 core tests · not enough evidence