---
base_model:
- Qwen/Qwen3-0.6B
- MultiverseComputing/LittleLamb-0.3B
library_name: transformers
license: apache-2.0
---
# LittleLamb 0.3B
### Powered by CompactifAI
[](https://opensource.org/licenses/Apache-2.0)
[](https://huggingface.co/MultiverseComputingCAI/LittleLamb)
[](https://discord.gg/cGas9uStqp)
**Tiny Model** · **50% Compressed** · **Thinking & Non-Thinking Modes**
---
## Table of Contents
- [Highlights](#highlights)
- [Model Overview](#model-overview)
- [Key Characteristics](#key-characteristics)
- [Quick Start](#quick-start)
- [What's New in LittleLamb 0.3B](#whats-new-in-littlelamb-03b)
- [Dual-Mode Inference (Thinking / Non-Thinking)](#dual-mode-inference-thinking--non-thinking)
- [Training & Fine-Tuning](#training--fine-tuning)
- [Architecture](#architecture)
- [Evaluation & Benchmarks](#evaluation--benchmarks)
- [Languages](#languages)
- [Intended Use](#intended-use)
- [Safety & Limitations](#safety--limitations)
- [Model Information](#model-information)
- [Citation](#citation)
---
## Model Overview
**LittleLamb 0.3B** is a **general-purpose bilingual model** at **290M parameters**, a similar size class to **270M** models such as **gemma3-270m-it** and **functiongemma-270m-it**—developed based on [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B), by **Multiverse Computing**. The original Qwen3-0.6B is an open-weight, instruction-tuned model with thinking and non-thinking capabilities and multilingual coverage. LittleLamb 0.3B is compressed at a **50% compression rate** using **CompactifAI**, Multiverse Computing's proprietary technology. The model supports **English and Spanish** and retains Qwen3's dual thinking/non-thinking modes.
---
## Key Characteristics
| Characteristic | Description |
| ---------------- | ---------------------------------------------------------------------------------------------------------------- |
| Base model | [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) (0.6B params, 0.44B non-embedding; open-weight, Apache 2.0) |
| **Parameters** | 290M total parameters after CompactifAI compression (50% compression rate from base 0.6B) |
| **Architecture** | Decoder-only Transformer (Qwen3 family) |
| **Compression** | CompactifAI (proprietary) |
| **Languages** | English and Spanish; inherits broader multilingual tokenizer coverage from Qwen3 |
| **Modes** | Thinking (`enable_thinking=True`) and non-thinking (`enable_thinking=False`) via chat template |
---
## Quick Start
This model can be loaded with the **Transformers** library. Requires `transformers>=4.51.0` for Qwen3 architecture support.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "MultiverseComputingCAI/LittleLamb"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
messages = [{"role": "user", "content": "Hello!"}]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True,
)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
output_ids = model.generate(**inputs, max_new_tokens=256)[0]
response = tokenizer.decode(
output_ids[len(inputs.input_ids[0]) :], skip_special_tokens=True
)
print(response)
```
For OpenAI-compatible serving, use a stack that supports Qwen3 reasoning (e.g. recent **vLLM** or **SGLang** with Qwen3 parsers); see the [Qwen3-0.6B model card](https://huggingface.co/Qwen/Qwen3-0.6B) for deployment examples.
---
## What's New in LittleLamb 0.3B
### Summary
- **Ultra-compact general-purpose model** at 290M parameters, suitable for edge and on-device deployment.
- **Developed based on [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)** with **CompactifAI** compression (~50% parameter reduction vs. base non-embedding count).
- **Bilingual focus:** English and Spanish for supported use cases.
---
## Dual-Mode Inference (Thinking / Non-Thinking)
LittleLamb 0.3B inherits Qwen3's dual-mode capability, supporting seamless switching between **thinking mode** (for complex reasoning) and **non-thinking mode** (for efficient general-purpose dialogue).
The model generates internal reasoning in Qwen3’s thinking format (see the Qwen3 chat template) before producing the final response. Use this for tasks requiring multi-step reasoning, math, or code generation.
Set `enable_thinking=False` for lower-latency dialogue without explicit chain-of-thought in the template. Follow the **sampling parameters** recommended in the [Qwen3-0.6B model card](https://huggingface.co/Qwen/Qwen3-0.6B) for each mode.
---
## Training & Fine-Tuning
### Base Model: Qwen3-0.6B
The base model [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) is a causal language model from the Qwen3 family, supporting thinking/non-thinking. See the [Qwen3 technical report](https://arxiv.org/abs/2505.09388) for details.
---
## Architecture
### Model Specifications
| Field | Value |
| ---------------- | ----------------------------------------------------------------------- |
| Base model | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) (0.6B params) |
| Total parameters |290M dense |
---
## Evaluation & Benchmarks
### Evaluation Methodology
Benchmark scores were obtained with the following setups. Methodology varies by benchmark family.
For **LittleLamb 0.3B** and **Qwen3-0.6B (base)**, benchmark runs are reported under both **thinking** and **non-thinking** chat modes using the sampling settings recommended in the [Qwen3-0.6B model card](https://huggingface.co/Qwen/Qwen3-0.6B).
#### MMLU-Pro, GPQA Diamond, HLE (Humanity's Last Exam)
- **Evaluation framework**: [Nemo-skills](https://github.com/NVIDIA/NeMo-Skills)
- **Inference library**: vLLM 0.18.0
- **Thinking mode** (`enable_thinking=True`, per Qwen3-0.6B instruct): temperature = 0.6, top_p = 0.95, top_k = 20, min_p = 0
- **Non-thinking mode** (`enable_thinking=False`, per Qwen3-0.6B instruct): temperature = 0.7, top_p = 0.8, top_k = 20, min_p = 0
### Quantitative Results (Reported & Planned)
Reported numbers use the methodology described above.
#### Thinking mode
| Benchmark | gemma3-270m-it | Qwen3-0.6B (think) | LittleLamb-0.3B (think) |
| ------------ | -------------- | ------------------ | ----------------------- |
| HLE | 4.00 | 5.65 | 6.12 |
| GPQA Diamond | 21.21 | 29.59 | 28.18 |
| MMLU-Pro | 6.23 | 38.27 | 31.21 |
#### Non-thinking mode
| Benchmark | gemma3-270m-it | Qwen3-0.6B (no think) | LittleLamb-0.3B (no think) |
| ------------ | -------------- | --------------------- | -------------------------- |
| HLE | 4.00 | 4.54 | 5.37 |
| GPQA Diamond | 21.21 | 27.77 | 24.04 |
| MMLU-Pro | 6.23 | 25.72 | 25.11 |


### Quantitative Results (Inference Performance)
#### Metrics reported
- **System Output Throughput (higher is better)**: Mean output tokens per second across all concurrent requests over the benchmarking phase.
- **End-to-End Latency per Query (lower is better):** Median end-to-end response time for each query from the time the query is sent.
- **Output Speed per Query (higher is better):** Median output tokens per second after the first token is received for each query.
- **Time to first token (TTFT) (lower is better):** Median
- **Estimated Peak Memory Usage (lower is better):** KV cache utilization is monitored during the phase and we estimate memory usage as follows: $model\_ weights_{gb} + kv\_ cache_{usage\_pct} × (nvml\_used_{gb} − model\_ weights_{gb})$
- **Model weights (lower is better):**
**Summary of improvements:** LittleLamb shows a slight improvement in performance with respect to the original Qwen Model. This is expected as for such small models, VRAM usage is dominated by KV cache and not model weights.
#### Performance evaluation conditions
Our performance evaluation follows the spirit of [Artificial Analysis](https://artificialanalysis.ai/methodology/system-load-test).
- **Inference library**: vLLM 0.18.0
- **Monitoring libraries**: GuideLLM 0.6.0, nvidia-ml-py 13.590.48
- **Hardware**: 1× NVIDIA L4 GPU
- **Conditions**: concurrency=16
- **Phase duration**: Each phase lasts 3 minutes (excluding ramp-up and cool-down periods).
- **Workload shape**: 1,000 input tokens and 1,000 output tokens per query.
- **Streaming**: Benchmarking is conducted with streaming enabled.
**Summary of improvements:** LittleLamb shows a slight improvement in performance with respect to the original Qwen Model. This is expected as for such small models, VRAM usage is dominated by KV cache and not model weights.

---
## Languages
- **Primary languages**: English and Spanish (supported for product use cases).
---
## Intended Use
### Recommended Use Cases
Aligned with [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) use cases, with the benefit of a smaller footprint suitable for edge and on-device deployment:
- **On-device and edge inference** where memory and compute are constrained
- **Reasoning tasks** with configurable thinking/non-thinking modes
- **Bilingual applications** (English and Spanish)
- **Chatbots and virtual assistants** in resource-constrained environments
- **General knowledge, math, and science** question answering
### Out-of-Scope Uses
- Harmful, illegal, or deceptive content generation
- Impersonation of real individuals without consent
- High-risk decision-making without human oversight
- Surveillance or tracking of individuals
- Any use that violates applicable laws or regulations
---
## Safety & Limitations
### Known Limitations
- **Model scale:** At ~0.3B parameters, this is an ultra-compact model. Several frontier-scale benchmarks (GDPval-AA, Terminal-Bench Hard, AA-LCR, CritPt) produce no discriminative signal at this model size, as the base Qwen3-0.6B itself scores near zero on them.
- **Thinking mode:** Performance differs substantially between thinking and non-thinking modes across benchmarks. Users should evaluate both modes for their specific use case.
### Recommendations
- Use human oversight for critical applications
- Perform task-specific evaluation prior to deployment
- Test both thinking and non-thinking modes for your use case
---
## Model Information
| Field | Value |
| ------------ | --------------------------------------------------------------------------- |
| Model name | LittleLamb |
| Based on | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) |
| Version | 2604 |
| Release date | 28/04/2026 |
| Developed by | Multiverse Computing |
| License | Apache 2.0 |
| Contact | [business@multiversecomputing.com](mailto:business@multiversecomputing.com) |
---
## Citation
If you use this model, please cite the base model and this variant:
```bibtex
@misc{qwen3technicalreport,
title = {Qwen3 Technical Report},
author = {Qwen Team},
year = {2025},
eprint = {2505.09388},
archivePrefix = {arXiv},
primaryClass = {cs.CL},
url = {https://arxiv.org/abs/2505.09388}
}
@misc{littlelamb,
title = {LittleLamb: Compressed Qwen3-0.6B via CompactifAI},
author = {Multiverse Computing},
year = {2026},
url = {https://huggingface.co/MultiverseComputingCAI/LittleLamb},
note = {Model developed based on Qwen/Qwen3-0.6B using CompactifAI technology}
}
```
**Built by [Multiverse Computing](https://www.multiversecomputing.com)** · [Report an issue](https://huggingface.co/MultiverseComputingCAI/LittleLamb/discussions) · [Discord](https://discord.gg/cGas9uStqp)