Unleash your creativity

Check our our current supported models below. We support the best, highest-rated models available, and we update the selection of models we support frequently. Sign up to receive a monthly update about our latest models and other news, and participate in our Discord Server to ask questions or request additional models.

TOP LLMS

TheDrummer/

Fallen Llama 3.3 R1 70B v1

RP, Storywriting
New
Doctor-Shotgun/

L3.3 70B Magnum v4 SE

"SE" for Special Edition, the objective, as with the other Magnum models, is to emulate the prose style and quality of the Claude 3 Sonnet/Opus series of models on a local scale.
New
Qwen/

Qwen3 235B A22B Thinking 2507

Enhanced reasoning power across logic, math, science, coding, and academic tasks with state-of-the-art results, combined with smarter instruction following, better tool usage, and high-quality text generation that’s more aligned with human style and preferences.
  • Qwen-Qwen3-235B-A22B-Thinking-2507
  • Context: 100K
New
Sophosympatheia/

Strawberrylemonade L3 70B v1.1

Sao10K/

70B L3.3 Cirrus x1

RP, Story Writing, Creative
  • Sao10K-70B-L3.3-Cirrus-x1
Anthracite-org/

Magnum-72b-v4

This model has spatial awareness, memory and detailed descriptions to keep the generation entertaining. Very good creativity and NSFW.

Settings provided by: GERGE

Sao10K/

72B Qwen2.5 Kunou v1

Another version of Euryale with with a Qwen base model.
rAIfle/

SorcererLM 8x22b bf16

Sao10K/

L3.3-70B-Euryale-v2.3

A direct replacement / successor to Euryale v2.2.
Sao10K/

L3.1 70B Hanami x1

  • GP, RP
  • FP16
  • Sao10K-L3.1-70B-Hanami-x1
  • Context: 32K

PLUS PLAN MODELS

All of Free + Essential + Standard and the following:

New
hexgrad/

Kokoro-82M

Kokoro is a Text to Speech model, which converts written text into natural-sounding speech using advanced AI voice synthesis. Simply type your text, select a voice, and generate high-quality audio in seconds. Join the discord to learn how to use this model.
  • TTS-hexgrad-Kokoro-82M
New
Top
Qwen/

Qwen3 235B A22B Thinking 2507

Enhanced reasoning power across logic, math, science, coding, and academic tasks with state-of-the-art results, combined with smarter instruction following, better tool usage, and high-quality text generation that’s more aligned with human style and preferences.
  • Qwen-Qwen3-235B-A22B-Thinking-2507
  • Context: 100K
New
Top
Sophosympatheia/

Strawberrylemonade L3 70B v1.1

Top
rAIfle/

SorcererLM 8x22b bf16

STANDARD PLAN MODELS

All of Free + Essential and the following:

Top
TheDrummer/

Fallen Llama 3.3 R1 70B v1

RP, Storywriting
New
Top
Doctor-Shotgun/

L3.3 70B Magnum v4 SE

"SE" for Special Edition, the objective, as with the other Magnum models, is to emulate the prose style and quality of the Claude 3 Sonnet/Opus series of models on a local scale.
Top
Anthracite-org/

Magnum-72b-v4

This model has spatial awareness, memory and detailed descriptions to keep the generation entertaining. Very good creativity and NSFW.

Settings provided by: GERGE

ESSENTIAL PLAN MODELS

All of Free and the following:

intfloat/

multilingual-e5-base

Embeddings model. This model is initialized from xlm-roberta-base and continually trained on a mixture of multilingual datasets. It supports 100 languages from xlm-roberta, but low-resource languages may see performance degradation. 512 Max context length.
  • intfloat-multilingual-e5-base
TheDrummer/

Valkyrie 49B V1

  • TheDrummer-Valkyrie-49B-v1
  • Context: 64K
  • RP
  • BF16
Top
Sao10K/

70B L3.3 Cirrus x1

RP, Story Writing, Creative
  • Sao10K-70B-L3.3-Cirrus-x1
Top
Sao10K/

72B Qwen2.5 Kunou v1

Another version of Euryale with with a Qwen base model.
Top
Sao10K/

L3.3-70B-Euryale-v2.3

A direct replacement / successor to Euryale v2.2.
Top
Sao10K/

L3.1 70B Hanami x1

  • GP, RP
  • FP16
  • Sao10K-L3.1-70B-Hanami-x1
  • Context: 32K
LatitudeGames/

Wayfarer 12B

Wayfarer is an adventure role-play model specifically trained to give players a challenging and dangerous experience.
  • LatitudeGames-Wayfarer-12B
meta-llama/

Meta Llama Guard 2 8B

Meta Llama Guard 2 is a safeguard model. It can be used for classifying content in both LLM inputs (prompt classification) and in LLM responses (response classification).
New
TheDrummer/

Anubis 70B v1.1

Finetune of llama 3.3.
Sao10K/

L3-70B-Euryale-v2.2

Coherent, emotional and very creative.

Settings provided by: ShotMisser64

TheDrummer/

UnslopNemo 12B v4.1

Qwen/

Qwen2.5-72B-Instruct

  • GP
  • FP8
  • Qwen2.5-72B-Instruct-Turbo
  • Context: 32K
Sophosympatheia/

Midnight Miqu 70B v1.5

Settings provided by: ShadingCrawler

Qwen/

Qwen2-72B-Instruct

  • BF16
  • GP
  • Qwen2.5-72B-Instruct
  • Context: 32K
meta-llama/

Llama-3.2-11B-Vision-Instruct

  • BF16
  • GP
  • Llama-3.2-11B-Vision-Instruct-Turbo
  • Context: 128K

FREE MODELS

Mistralai/

Mixtral 8x7B Instruct v0.1

  • BF16
  • GP
  • Mixtral-8x7B-Instruct-v0.1
  • Context: 32K
TheDrummer/

Rocinante-12B-v1.1

  • RP
  • BF16
  • TheDrummer-Rocinante-12B-v1.1
  • Context: 32K

GUIDES

L3 Euryale 70B v2.1

Models

L3-70B-Euryale-v2.1

Meet L3 70B Euryale v2.1: Your New Creative Companion What is L3 70B Euryale v2.1 [...]

20
Aug

Guides

Using Infermatic.ai API with SillyTavern

SillyTavern is one of the most popular interfaces to interact with LLMs. We have been [...]

21
Jun

Models

nvidia/Llama-3.1-Nemotron-70B-Instruct

Llama 3.1 Nemotron 70B Instruct: Follow and assert Llama 3.1 Nemotron 70B Instruct is NVIDIA’s [...]

06
Dec
inferor

Models

Infermatic/MN 12B Inferor v0.0

MN 12B Inferor v0.0: Dynamic and Creative MN 12B Inferor, also known as Mistral Nemo [...]

05
Dec

Docs