No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from MultiverseComputingCAI/LittleLamb-ToolCalling
All models by MultiverseComputingCAI →
Tiny Model · 50% Compressed · Native Tool Calling · Thinking & Non-Thinking Modes
LittleLamb 0.3B Tool-Calling is a tool-calling–optimized variant of LittleLamb 0.3B at 290M parameters, developed based on Qwen3-0.6B by Multiverse Computing. Built on top of the CompactifAI-compressed LittleLamb base, this variant has been additionally fine-tuned for function calling, structured outputs, and agentic workflows. It supports thinking and non-thinking modes while adding native tool-use support in a sub-300M-parameter footprint.
This model can be loaded with the Transformers library. Requires transformers>=4.51.0 for Qwen3 architecture support.
For OpenAI-compatible serving, use a stack that supports Qwen3 reasoning and tool calling (e.g. recent vLLM or SGLang with Qwen3 parsers); see the Qwen3-0.6B model card for deployment examples.
LittleLamb 0.3B Tool-Calling supports native tool use and is designed for:
The model can detect when to invoke tools, emit structured JSON tool calls, and consume tool outputs to continue generation. Tool-calling behavior follows Qwen3-style schemas.
LittleLamb 0.3B Tool-Calling 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 for each mode.
The base model Qwen3-0.6B is a causal language model from the Qwen3 family, supporting thinking/non-thinking modes. See the Qwen3 technical report for details.
Benchmark scores were obtained with the following setups. Methodology varies by benchmark family.
For LittleLamb 0.3B Tool-Calling 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.
enable_thinking=True, per Qwen3-0.6B instruct): temperature = 0.6, top_p = 0.95, top_k = 20, min_p = 0enable_thinking=False, per Qwen3-0.6B instruct): temperature = 0.7, top_p = 0.8, top_k = 20, min_p = 0enable_thinking=True, per Qwen3-0.6B instruct): temperature = 0.6, top_p = 0.95, top_k = 20, min_p = 0enable_thinking=False, per Qwen3-0.6B instruct): temperature = 0.7, top_p = 0.8, top_k = 20, min_p = 0functiongemma-270m-it for BFCL v4 were extracted from Google's model card (09/04/2026)Reported numbers use the methodology described above.
[Image blocked: Intelligence Thinking]
BFCL V4 is the de facto industry standard for evaluating function-calling (tool-use) capability. It tests whether models can correctly generate structured function calls in response to user queries, across simple single-call scenarios, parallel calls, multi-turn conversations, and complex agentic workflows.
Our performance evaluation follows the spirit of Artificial Analysis.
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.
[Image blocked: Performance]
Aligned with Qwen3-0.6B use cases, with the added benefit of tool-calling capabilities in a smaller footprint suitable for edge and on-device deployment:
If you use this model, please cite the base model and this variant:
Built by Multiverse Computing · Report an issue · Discord
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "MultiverseComputingCAI/LittleLamb-ToolCalling"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){ "name": "get_weather", "arguments": { "city": "Paris", "date": "2026-02-10" }}@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{littlelambtc, title = {LittleLamb Tool-Calling: Compressed Qwen3-0.6B with Tool-Use via CompactifAI}, author = {Multiverse Computing}, year = {2026}, url = {https://huggingface.co/MultiverseComputingCAI/LittleLamb-ToolCalling}, note = {Model developed based on Qwen/Qwen3-0.6B using CompactifAI technology, fine-tuned for tool calling}}