COMPARE.

nousresearch

Nous-Hermes-2-Mixtral-8x7B-DPO

Models

Context window

32,768 tokens

Total parameters

46.70 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence

nousresearch

Nous-Hermes-2-Mixtral-8x7B-SFT

Models

Context window

32,768 tokens

Total parameters

46.70 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence

nousresearch

Nous-Hermes-2-SOLAR-10.7B

Models

Context window

4,096 tokens

Total parameters

10.73 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence

nousresearch

Nous-Hermes-2-Yi-34B

Models

Context window

4,096 tokens

Total parameters

34.39 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence

nousresearch

NousCoder-14B

Models

Context window

81,920 tokens

Total parameters

14.77 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/baidu/ernie-4.5-21B-a3b-thinking

Models^*

Maximum output

65,536 tokens^*

Maximum input

131,072 tokens^*

Reasoning

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/deepseek/deepseek-r1-0528-qwen3-8b

Models^*

Maximum output

32,000 tokens^*

Maximum input

128,000 tokens^*

Reasoning

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/google/gemma-3-27b-it

Models^*

Maximum output

16,384 tokens^*

Maximum input

98,304 tokens^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/meta-llama/llama-3-8b-instruct

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/meta-llama/llama-3.1-8b-instruct

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/meta-llama/llama-3.2-1b-instruct

Models^*

Maximum output

32,000 tokens^*

Maximum input

131,000 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/meta-llama/llama-4-scout-17b-16e-instruct

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/microsoft/wizardlm-2-8x22b

Models^*

Maximum output

8,000 tokens^*

Maximum input

65,535 tokens^*

Structured output

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/paddlepaddle/paddleocr-vl

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen2.5-vl-72b-instruct

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-32b-fp8

Models^*

Maximum output

20,000 tokens^*

Maximum input

40,960 tokens^*

Reasoning

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/qwen/qwen3-8b-fp8

Models^*

Maximum output

20,000 tokens^*

Maximum input

128,000 tokens^*

Reasoning

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

novita/zai-org/autoglm-phone-9b-multilingual

Models^*

Maximum output

65,536 tokens^*

Maximum input

65,536 tokens^*

API mode

Chat^*

Image input

Yes^*

Radar · unrated0/4 core tests · not enough evidence

nvidia

NVLM-D-72B

Models

Context window

131,072 tokens

Open weights

Yes

Model license

cc-by-nc-4.0

Checkpoint tensor payload

164.75 GiB

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.command-a-reasoning-08-2025

Models^*

Maximum output

4,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

Yes^*

Structured output

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.command-a-translate-08-2025

Models^*

Maximum output

4,000 tokens^*

Maximum input

256,000 tokens^*

Tool calling

No^*

Structured output

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.command-r-08-2024

Models^*

Maximum output

4,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/cohere.command-r-plus-08-2024

Models^*

Maximum output

4,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

oci/meta.llama-3.3-70b-instruct-fp8-dynamic

Models^*

Maximum output

4,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

Structured output

No^*

Radar · unrated0/4 core tests · not enough evidence