Instructions to use saishshinde15/Clyrai_Maximus-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saishshinde15/Clyrai_Maximus-MoE with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="saishshinde15/Clyrai_Maximus-MoE", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("saishshinde15/Clyrai_Maximus-MoE", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use saishshinde15/Clyrai_Maximus-MoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saishshinde15/Clyrai_Maximus-MoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saishshinde15/Clyrai_Maximus-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/saishshinde15/Clyrai_Maximus-MoE

SGLang

How to use saishshinde15/Clyrai_Maximus-MoE with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "saishshinde15/Clyrai_Maximus-MoE" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saishshinde15/Clyrai_Maximus-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "saishshinde15/Clyrai_Maximus-MoE" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saishshinde15/Clyrai_Maximus-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use saishshinde15/Clyrai_Maximus-MoE with Docker Model Runner:
```
docker model run hf.co/saishshinde15/Clyrai_Maximus-MoE
```

Clyrai Maximus — 110 million parameters. Per token.

The rest of the model is silent.

Every language model you know lights up everything it has, for every word it says.

Maximus does not.

It is Clyrai's first Mixture of Experts. Two hundred and sixty-four million parameters on disk. One hundred and ten million fire for a token. Thirty-two specialists. Four speak. The others wait.

That is not a compression trick. That is the architecture.

Decode is the product.

Prefill is a parallel trick. Impressive. Irrelevant.

What you feel is the next token. Then the next. The GPU is not thinking. It is waiting on memory.

decode tok/s  =  bandwidth  /  (active parameters × 2 bytes)

So Maximus is not "a small model." It is a sparse machine.


NVIDIA RTX PRO 5000 Blackwell	6,104 tokens / second
MacBook Air M1	310 tokens / second

Same law. Different pipe.

A dense 264M would drag every expert across that pipe. Maximus moves 2.4× less per word. Five hundred and four megabytes. The whole thing.

First token in 31 milliseconds. Then it streams.

Thirty-two experts. Four at a time.

No committee. A router.

Sigmoid. Top-4. One shared expert that always shows up. The first two layers stay dense — a quiet hallway before the hall of specialists.

It was trained that way from nothing. Not adapted. Not distilled from a giant. From scratch.

5.2 billion unique tokens. English. हिंदी. Italiano. Code. One hundred and twenty-eight thousand tokens of context.

Every expert lives. None of them died in training. That is rarer than it sounds.

Use it.

Maximus is a completion model. Give it a sentence that has already begun. Greedy decoding without a repetition penalty will loop — that is baked into generation_config.json so the defaults are the Clyrai defaults.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "saishshinde15/Clyrai_Maximus-MoE"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    trust_remote_code=True,
).cuda()

def complete(prompt: str) -> str:
    ids = tok(prompt, return_tensors="pt").to(model.device)
    out = model.generate(**ids, max_new_tokens=64)
    return tok.decode(out[0], skip_special_tokens=True)

print(complete("In a statement on Monday, the government"))
print(complete("भारत की राजधानी"))

trust_remote_code=True is required. This is not a dense Llama export. A Llama conversion would drop the experts.

MacBook (Apple Silicon)

No CUDA. Use MPS. On an 8 GB Air, quit other apps first — the weights are 504 MiB.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "saishshinde15/Clyrai_Maximus-MoE"
device = torch.device("mps" if torch.backends.mps.is_available() else "cpu")
dtype = torch.float16 if device.type == "mps" else torch.float32

tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype=dtype,
    trust_remote_code=True,
).to(device)

def complete(prompt: str) -> str:
    ids = tok(prompt, return_tensors="pt")
    ids = {k: v.to(device) for k, v in ids.items()}
    out = model.generate(**ids, max_new_tokens=64)
    return tok.decode(out[0], skip_special_tokens=True)

print(complete("In a statement on Monday, the government"))
print(complete("भारत की राजधानी"))

Or from this repo: python3 scripts/run_maximus_mac.py

One more thing.

This is the engine.

Not the assistant. Not the personality. Not the voice that says hello.

Clyrai built the sparse foundation first — because inference is the only moment the user is in the room. Chat comes after. The Mixture is already here.

The work is ours.

The weights are public. The title is not.

Study it. Cite it. Do not take it. Research and personal evaluation, with credit. Commerce, distillation, hosted product use, and training another model on Maximus require a grant from Clyrai.

All other rights reserved.

Clyrai Sovereign Research License 1.0

Clyrai

The numbers, for the curious


Total / active	264M / 110M
Experts	32 · top-4 · 1 shared
Layers	16 · first 2 dense
Context	131,072
Size	504 MiB bf16
Tokens	5.18B unique · no epoching
Mix	55% EN · 20% code · 15% HI · 10% IT
Train / held-out CE	0.97 / 1.03
Routing	32/32 live
Checkpoint	`step9879` · base, not instruct

Downloads last month: 807

Safetensors

Model size

0.3B params

Tensor type

F32

BF16