COMPARE.

alibaba

Qwen3-VL-8B-Instruct

Models

Context window

262,144 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

16.33 GiB

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen3-VL-8B-Thinking

Models

Context window

262,144 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

16.33 GiB

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen3.5-0.8B-Base

Models

Context window

262,144 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

1.63 GiB

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen3.5-2B-Base

Models

Context window

262,144 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

4.24 GiB

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen3.5-4B-Base

Models

Context window

262,144 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

8.68 GiB

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen3Guard-Gen-8B

Models

Context window

32,768 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

15.26 GiB

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwencloud/qwen3-30b-a3b

Models^*

Maximum output

16,384 tokens^*

Maximum input

129,024 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-2-13b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-2-13b-chat

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-2-70b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-2-70b-chat

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-2-7b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-2-7b-chat

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-3-70b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-3-70b-instruct

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/meta/llama-3-8b

Models^*

Maximum output

8,086 tokens^*

Maximum input

8,086 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

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

Models^*

Maximum output

8,086 tokens^*

Maximum input

8,086 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/mistralai/mistral-7b-instruct-v0.2

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/mistralai/mistral-7b-v0.1

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

replicate/mistralai/mixtral-8x7b-instruct-v0.1

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Tool choice

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

rerank-english-v3.0

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

rerank-multilingual-v3.0

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

rerank-v3.5

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

rerank-v4.0-fast

Models^*

Maximum output

32,768 tokens^*

Maximum input

32,768 tokens^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence