Instructions to use AlreadyAI/Bala-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlreadyAI/Bala-30B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="AlreadyAI/Bala-30B-A3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlreadyAI/Bala-30B-A3B")
model = AutoModelForCausalLM.from_pretrained("AlreadyAI/Bala-30B-A3B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AlreadyAI/Bala-30B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlreadyAI/Bala-30B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlreadyAI/Bala-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AlreadyAI/Bala-30B-A3B

SGLang

How to use AlreadyAI/Bala-30B-A3B 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 "AlreadyAI/Bala-30B-A3B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlreadyAI/Bala-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "AlreadyAI/Bala-30B-A3B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlreadyAI/Bala-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AlreadyAI/Bala-30B-A3B with Docker Model Runner:
```
docker model run hf.co/AlreadyAI/Bala-30B-A3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Bala v1 (30B-A3B)

Bala v1 is a coding-and-reasoning model developed by TushLab, the model lab of AlreadyAI. It is produced by attention-only QLoRA fine-tuning of Qwen3-30B-A3B-Thinking-2507 (MoE, ~30B total / ~3B active parameters) on a small mixture of open reasoning-distillation corpora. It is an honest proof-of-capability release: a real, decontaminated improvement in mathematics over its base, with no claim of a coding gain and no frontier claim.

Repository: AlreadyAI/Bala-30B-A3B · Release: v1.0
Developed by: TushLab (AlreadyAI)

Transparency: Bala is a fine-tune of the Apache-2.0 model Qwen/Qwen3-30B-A3B-Thinking-2507. It is trained to self-identify as "Bala, made by TushLab"; the underlying base is disclosed here and in the accompanying report.

Files & usage

This repo ships both the fully-merged model (at the repo root — load directly) and the standalone LoRA adapters (adapters/). adapters/checkpoint-2556 is the released epoch-3 winner; checkpoint-1700 is the epoch-2 checkpoint. The merged weights and (adapter + base) are equivalent.

Direct (merged weights):

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("AlreadyAI/Bala-30B-A3B")
model = AutoModelForCausalLM.from_pretrained("AlreadyAI/Bala-30B-A3B",
                                             torch_dtype="auto", device_map="auto")

Adapter on the base (equivalent):

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = "Qwen/Qwen3-30B-A3B-Thinking-2507"
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, "AlreadyAI/Bala-30B-A3B",
                                  subfolder="adapters/checkpoint-2556")

What it is / isn't

Is: a math-reasoning booster. On MATH-500, pass@1 improves 53.6 → 77.2 (+23.6) over the base.
Isn't: a coding improvement (HumanEval+ −3.7, MBPP+ +3.4, GSM8K flat near ceiling), and not competitive with closed frontier models. See Evaluation.

Evaluation (greedy pass@1, full sets)

Benchmark	n	Base	Bala	Δ
GSM8K	1,319	95.6	94.2	−1.4
MATH-500	500	53.6	77.2	+23.6
HumanEval+	164	78.7	75.0	−3.7
MBPP+	378	86.0	89.4	+3.4
Overall	2,361	84.0	88.5	+4.5

Base = unmodified Qwen3-30B-A3B-Thinking-2507, evaluated identically. Full methodology, the 4-config hyperparameter comparison, and eval logs are in the technical report and results/.

Decontamination

We ran n-gram containment + exact/substring matching between the entire data pool and all four benchmarks. The data this model was trained on (offline corpora + identity) is clean against all four benchmarks at n=13 and the stricter n=8. (An auxiliary pool of self-generated traces, not used to train this model, contained ~12% MBPP+ overlap; it is disclosed in the paper and is not part of this model's training data.) Report: results/decontamination/report.json. Method: n-gram/exact only — does not catch deep paraphrase.

Training

Method: QLoRA, 4-bit NF4 base / bf16 compute, LoRA on q,k,v,o_proj only (MoE expert MLPs frozen). Config B: rank 128, α 256, LR 2.5e-4, cosine, warmup 0.03, 3 epochs, seq-len 4096, effective batch 16, seed 0.
Data: 15,296 examples — OpenCodeReasoning (3k), Mixture-of-Thoughts code/math/science (3k each), OpenThoughts3 (3k), identity (296). Offline traces treated as verified-by-construction (not re-executed).
Hardware: 1× AWS g6e.12xlarge (4× L40S 48 GB, no NVLink), single-GPU per config.

Intended use & limitations

Research and experimentation on math/reasoning tasks. Single-seed results (no variance reported); coding is not improved over base; identity data is mixed in (model presents as "Bala"). Not for high-stakes use without independent evaluation. Inherits the base model's licenses, biases, and context behavior.

License

Apache-2.0 (base and all released artifacts).

Paper

Technical report: "Distilling Open Reasoning Corpora into a 3B-Active MoE on Commodity GPUs: What Transfers, What Doesn't, and a Decontamination Check" — published on Zenodo, DOI 10.5281/zenodo.22552056 (Apache-2.0 / CC BY 4.0). Full text also in paper/.

Citation

@misc{chauhan2026bala,
  title  = {Distilling Open Reasoning Corpora into a 3B-Active MoE on Commodity GPUs: What Transfers, What Doesn't, and a Decontamination Check},
  author = {Chauhan, Tushar},
  year   = {2026},
  publisher = {Zenodo},
  doi    = {10.5281/zenodo.22552056},
  url    = {https://doi.org/10.5281/zenodo.22552056}
}

Downloads last month: 191

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for AlreadyAI/Bala-30B-A3B

Base model

Qwen/Qwen3-30B-A3B-Thinking-2507

Finetuned

(41)

this model

Quantizations

2 models

AlreadyAI
/

Bala-30B-A3B