Instant, unlimited hosting for any Llama model on HuggingFace.
No servers needed.

Over 2700+ compatible models to choose from.
Starting from $10/month.

Most Popular Models

The most popular models on the platform in the last 2 weeks.

mistral-nemo-12b-lc
MarinaraSpaghetti/NemoMix-Unleashed-12B
#1
Warm
153
5,543
qwen2-72b-lc
Qwen/Qwen2.5-72B-Instruct
#2
Warm
569
289,009
llama31-70b-16k
meta-llama/Meta-Llama-3.1-70B-Instruct
#3
Warm
733
1,425,467
qwen2-32b-lc
EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
#4
Warm
37
2,279
llama31-70b-16k
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
#5
Warm
1,796
162,898
qwen2-72b-lc
EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
#6
Warm
9
664
mistral-nemo-12b-lc
GalrionSoftworks/MN-LooseCannon-12B-v1
#7
Warm
8
698
llama31-70b-16k
Sao10K/L3.1-70B-Hanami-x1
#8
Warm
26
696
qwen2-72b-lc
sophosympatheia/Evathene-v1.3
#9
Warm
13
400
llama31-70b-16k
allenai/Llama-3.1-Tulu-3-70B
#10
Warm
43
1,888
mistral-nemo-12b-lc
ProdeusUnity/Stellar-Odyssey-12b-v0.0
#11
Warm
11
59
llama3-70b-8k
NeverSleep/Llama-3-Lumimaid-70B-v0.1
#12
Warm
29
116
qwen2-72b-lc
sophosympatheia/Evathene-v1.0
#13
Warm
21
608
llama31-70b-16k
Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B
#14
Warm
5
138
qwen2-72b-lc
EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
#15
Warm
12
628
llama3-70b-8k
sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0
#16
Warm
50
116
mistral-nemo-12b-lc
VongolaChouko/Starcannon-Unleashed-12B-v1.0
#17
Warm
34
553
qwen2-72b-lc
anthracite-org/magnum-v4-72b
#18
Warm
24
1,076
mistral-nemo-12b-lc
Trappu/Magnum-Picaro-0.7-v2-12b
#19
Warm
7
169
qwen2-72b-lc
KaraKaraWitch/MachiNoDolphin-Qwen2.5-72b
#20
Warm
2
96

Trending this Week

The currently trending models that are growing in popularity this week.

qwen2-72b-lc
sophosympatheia/Evathene-v1.3
#1
Warm
13
400
qwen2-72b-lc
sophosympatheia/Evathene-v1.2
#2
Warm
2
131
llama31-70b-16k
meta-llama/Llama-3.3-70B-Instruct
#3
Warm
633
26,987
qwen2-72b-lc
Sao10K/72B-Qwen2.5-Kunou-v1
#4
Warm
11
173
llama31-70b-16k
unsloth/Llama-3.3-70B-Instruct
#5
Warm
17
23,250
llama31-70b-16k
Blackroot/Mirai-70B-1.0
#6
Warm
2
30
llama31-70b-16k
Sao10K/L3.3-70B-Euryale-v2.3
#7
Warm
18
104
llama31-8b-16k
DavidAU/L3.1-RP-Hero-Dirty_Harry-8B
#8
Warm
2
64
mistral-nemo-12b-lc
Khetterman/DarkAtom-12B-v3
#9
Warm
12
138
llama31-70b-16k
sandbox-ai/Llama-3.1-Tango-70b
#10
Warm
6
152
mistral-v02-7b-std-lc
AIDC-AI/Marco-o1
#11
Warm
631
12,798
llama31-70b-16k
Model-SafeTensors/Llama-3.1-Tango-70b
#12
Warm
0
46
mistral-nemo-12b-lc
Svak/MN-12B-Inferor-v0.1
#13
Warm
1
292
llama2-solar-10b7-4k
Weyaxi/HelpSteer-filtered-Solar-Instruct
#14
Warm
0
769
llama31-8b-16k
sandbox-ai/Llama-3.1-Tango-8b-f16
#15
Warm
0
25
llama3-70b-8k
Bllossom/llama-3-Korean-Bllossom-70B
#16
Warm
76
595
llama3-70b-8k
dmis-lab/llama-3-meerkat-70b-v1.0
#17
Warm
6
156

Latest Models

These are the most recently available models in Featherless

llama3-8b-8k
rudradhar/autotrain-llama-1-merged
Cold
0
113
llama31-8b-16k
yuchenxie/ArlowGPT-8B
Warm
2
132
qwen2-72b-lc
pankajmathur/orca_mini_v7_72b
Cold
11
3,073
llama31-70b-16k
nitky/Llama-3.1-SuperSwallow-70B-Instruct-v0.1
Cold
1
123
llama31-70b-16k
Sao10K/L3.3-70B-Euryale-v2.3
Warm
18
104
llama31-70b-16k
Blackroot/Mirai-70B-1.0
Warm
2
30
llama31-8b-16k
sandbox-ai/Llama-3.1-Tango-8b-f16
Warm
0
25
llama31-8b-16k
neuralmagic/Sparse-Llama-3.1-8B-evolcodealpaca-2of4
Cold
0
115
llama31-8b-16k
mlfoundations-dev/OH_original_wo_evol_instruct_70k
Cold
0
101
llama31-8b-16k
mlfoundations-dev/OH_DCFT_V3_wo_collective_cognition
Cold
0
100
llama3-8b-8k
HINT-lab/llama3-8b-final-ppo-clean-v0.1
Cold
0
102
mistral-nemo-12b-lc
Svak/MN-12B-Inferor-v0.1
Warm
1
292
llama31-70b-16k
unsloth/Llama-3.3-70B-Instruct
Warm
18
23,250
qwen2-72b-lc
Sao10K/72B-Qwen2.5-Kunou-v1
Warm
11
173
llama31-8b-16k
mlfoundations-dev/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp
Cold
0
133
llama3-8b-8k
Dhana8907/labsmergedModel0312
Cold
0
161
llama31-8b-16k
violetxi/sft_tir_3e-5_b32_warmup0.1_checkpoint-epoch2
Cold
0
346
llama31-8b-16k
violetxi/sft_tir_3e-5_b32_warmup0.1_checkpoint-epoch1
Cold
0
150
llama31-8b-16k
violetxi/sft_tir_3e-5_b32_warmup0.1_checkpoint-epoch0
Cold
0
296
llama31-8b-16k
DongfuJiang/prm_gsm_2k_with_full_sol_mix_ref_redistribution_hf
Cold
0
380

Trusted by developers at

Hugging Face
Coframe.com
Elevenlabs
Latitude.io
lightspeed
Resaro.ai
Dali.games
Alterhq.com

Simple Pricing Unlimited Tokens

Feather Basic

Max. 15B

$ 10 USD / Month

  • Unlimited Personal Use*
  • Ever growing list of community models
  • New models added weekly
  • Access to all models in the Feather ecosystem every month
  • Private, secure, and anonymous usage - no logs
*Personal Use is a maximum of 2 concurrent requests.

Feather Premium

Max. 72B

$ 25 USD / Month

  • All the benefits of Feather Basic
  • Up to 72B models*
*70B & 72B have a maximum of 1 concurrent requests. 15B and smaller have a maximum of 3 concurrent requests
Need more concurrent requests?

Feather Scale

Max. 72B

$ 75 USD / Month

  • All the benefits of Feather Premium
  • Scalable pricing to meet your needs
  • Host your own private models from Hugging Face
Concurrency is scaled based on quantity of the selected plan.

How many concurrencies do you need?

250
2× Premium Models
or 6× Basic Models

Feather Enterprise

Custom

  • Run your entire catalog.
  • From your cloud.
  • With reduced GPUs.

Frequently Asked Questions

What is Featherless?

Featherless is an LLM hosting provider that offers our subscribers access to a continually expanding library of Hugging Face models.

Featherless: Less hassle, less effort. Start now.

What does it cost?

We offer two pricing plans at $10 and $25 a month.

If the concurrency limits are too restrictive for genuine personal use, please reach out to us via our Discord.

Are my logs stored?

No. As a privacy-focused service, we do not log any of your chats, prompts, or completions. Please see our privacy policy for more details.

Which model architectures are supported?

At present, we support LLaMA-3-based models, including LLaMA-3 and QWEN-2.

Note that QWEN-2 models are only supported up to 16,000 context length.

We plan to add more architectures to our supported list soon.

How do I get new models added?

Ping us on our Discord.

We continuously onboard new models as they become available on Hugging Face.

As we grow, we aim to automate this process to encompass all publicly available Hugging Face models with compatible architectures.

How unlimited is unlimited?

As long as you remain subscribed, there's no time cap on model usage.

To ensure fair individual account use, concurrent requests are limited according to the plan you've selected.

Output is delivered at a speed of 10-40 tokens per second, depending on the model and prompt size.

How can I get in touch?

Join our Discord or find us on r/SillyTavernAI.

Are you running quantized models?

Yes, we use FP8 quantization.

After consulting with the community, we've found that this approach maintains output quality while significantly improving inference speeds.

How are you able to run so many models?

At the heart of the platform is our custom inference stack, in which we can dynamically swap out models on the fly in <1 second for a 10B model.

This allows us to rapidly reconfigure our infrastructure according to user workload and autoscale accordingly, as a single unified unit.

Why would I not just use Hugging Face or etc. directly?

Cost, speed, and customization

While Hugging Face and RunPod let you run any model, they charge $1 per hour or higher for the GPUs. If you plan on using models for over five hours consistently, using our platform is likely the more affordable option.

On the flip side, other providers may offer a limited list of models to optimize for cost and speed. But they may not have the model you want.

Do you have a referral program?

Yes! Refer a friend, and when they subscribe and add your email, both of you get $10 OFF your next monthly bill!

Refer 12 of your friends and you can have a full year off our basic plan! (The discount stacks!)

Details here.

Some of your models don't have open licenses (e.g. CC-BY-NC); how can these be listed on your site?

We are a serverless AI hosting provider. Our product simplifies the process of deploying models from Hugging Face. We are not charging for the underlying models.

We list all supported models, any of which can be made available for inference in milliseconds. We interpret all API requests as model allocation requests and "deploy" the underlying model automatically. This is analogous to how an individual would use RunPod, but at a different scale.

Moreover, we are in contact with model creators of the most popular models to avoid misunderstandings about the nature of Featherless, and have obtained their permission. If you are a model creator and take issue with a listing here, please contact us at hello@featherless.ai.

Support Open Source AI!

The Recursal AI team's primary goal is to make Open Source AI accessible to everyone, regardless of language or economic status.

That's why we work actively to build open source AI models with the RWKV community that are multi-lingual, highly scalable, and affordable.
The revenue we make from Featherless AI helps support our work in training and scaling such models. You can see our latest open source AI model here.

Also, we encourage you to reach out to your favorite model creators to support them directly as well.