Janhq

14 indexed models

14 matching models

janhq/Jan-code-4b

vertexAI/publishers/hf-janhq/models/jan-code-4b@001

Input modalities
text
Output modalities
text

janhq/Jan-v1-2509

vertexAI/publishers/hf-janhq/models/jan-v1-2509@001

Input modalities
text
Output modalities
text

janhq/Jan-v1-4B

vertexAI/publishers/hf-janhq/models/jan-v1-4b@001

Input modalities
text
Output modalities
text

janhq/Jan-v1-edge

vertexAI/publishers/hf-janhq/models/jan-v1-edge@001

Input modalities
text
Output modalities
text

janhq/Jan-v2-VL-high

azureFoundry/HuggingFace/janhq-jan-v2-vl-high@1

`janhq/Jan-v2-VL-high` powered by vLLM - [Original Model Card](https://huggingface.co/janhq/Jan-v2-VL-high) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a request to the Azure ML endpoint wi

Input modalities
text
Output modalities
text

janhq/Jan-v2-VL-low

azureFoundry/HuggingFace/janhq-jan-v2-vl-low@1

`janhq/Jan-v2-VL-low` powered by vLLM - [Original Model Card](https://huggingface.co/janhq/Jan-v2-VL-low) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a request to the Azure ML endpoint with

Input modalities
text
Output modalities
text

janhq/Jan-v2-VL-med

azureFoundry/HuggingFace/janhq-jan-v2-vl-med@1

`janhq/Jan-v2-VL-med` powered by vLLM - [Original Model Card](https://huggingface.co/janhq/Jan-v2-VL-med) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a request to the Azure ML endpoint with

Input modalities
text
Output modalities
text

janhq/Jan-v3.5-4B

vertexAI/publishers/hf-janhq/models/jan-v3.5-4b@001

Input modalities
text
Output modalities
text

janhq/supermario-slerp

huggingface/janhq/supermario-slerp

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 72.325%

janhq/supermario-slerp-v2

huggingface/janhq/supermario-slerp-v2

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 71.351%

janhq/supermario-v1

huggingface/janhq/supermario-v1

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 29.493%

janhq/supermario-v2

huggingface/janhq/supermario-v2

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 72.339%

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace