LittleLamb 0.3B Tool-Calling is a tool-calling–optimized variant of LittleLamb 0.3B at 290M parameters, developed based on Qwen3-0.6Bby 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.
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.
What's New in LittleLamb 0.3B Tool-Calling
Summary
Tool-calling–optimized variant of LittleLamb 0.3B, fine-tuned for function calling and structured outputs.
Ultra-compact at 290M parameters, suitable for edge and on-device deployment with agentic capabilities.
Developed based on Qwen3-0.6B with CompactifAI compression (~50% parameter reduction vs. base non-embedding count).
Tool Calling
LittleLamb 0.3B Tool-Calling supports native tool use and is designed for:
Function calling with defined schemas
Structured outputs
Agentic operations (e.g. browser tasks, code execution where supported)
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.
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.
Training & Fine-Tuning
Base Model: Qwen3-0.6B
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.
Compression: CompactifAI was applied to produce a smaller, efficient model (~0.3B parameters) while aiming to preserve reasoning capabilities.
Tool-calling fine-tuning: This variant includes additional fine-tuning for function calling and structured outputs on top of the compressed LittleLamb base.
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.
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
Results of functiongemma-270m-it for BFCL v4 were extracted from Google's model card (09/04/2026)
Quantitative Results
Reported numbers use the methodology described above.
Thinking mode
Benchmark
functiongemma-270m-it
Qwen3-0.6B (think)
LittleLamb-TC 0.3B (think)
IFBench
12.00
23.88
20.00
GPQA Diamond
2.53
29.59
27.47
MMLU-Pro
0.42
38.27
28.74
τ²-Bench
5.05
19.59
18.70
BFCL Simple
61.60
72.73
72.36
BFCL Multiple
63.50
85.00
89.50
BFCL Parallel
39.00
70.00
70.00
BFCL Parallel Multiple
29.50
71.50
68.00
BFCL Live Simple
36.20
63.18
64.34
BFCL Live Multiple
25.70
56.41
60.78
BFCL Live Parallel
22.90
50.00
62.50
BFCL Live Parallel Multiple
20.80
50.00
45.83
BFCL Relevance
61.10
75.00
75.00
BFCL Irrelevance
73.70
84.58
77.92
BFCL v4
27.03
54.08
51.55
Non-thinking mode
Benchmark
functiongemma-270m-it
Qwen3-0.6B (no think)
LittleLamb-TC 0.3B (no think)
IFBench
12.00
23.80
21.00
GPQA Diamond
2.53
27.77
27.37
MMLU-Pro
0.42
25.72
23.71
τ²-Bench
5.05
15.50
26.67
BFCL Simple
61.60
12.73
70.55
BFCL Multiple
63.50
20.00
80.50
BFCL Parallel
39.00
18.00
71.50
BFCL Parallel Multiple
29.50
30.50
70.50
BFCL Live Simple
36.20
4.65
62.02
BFCL Live Multiple
25.70
11.02
50.43
BFCL Live Parallel
22.90
0.00
43.75
BFCL Live Parallel Multiple
20.80
12.50
29.17
BFCL Relevance
61.10
12.50
75.00
BFCL Irrelevance
73.70
97.50
87.50
BFCL v4
27.03
29.17
50.51
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.
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: $model_ weights_{gb} + kv_ cache_{usage_pct} × (nvml_used_{gb} − model_ weights_{gb})$
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.
Performance
Languages
Primary languages: English. Spanish is yet to be tested for tool-calling capabilities.
Intended Use
Recommended Use Cases
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:
Function calling and agentic workflows in resource-constrained environments
On-device and edge inference where memory and compute are constrained
Structured output generation (JSON, schemas)
Reasoning tasks with configurable thinking/non-thinking modes
Chatbots and virtual assistants with tool integration
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.
Tool calling: While fine-tuned for tool use, accuracy and reliability of tool calls should be validated for production use cases given the model's compact size.
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
Validate tool-call outputs before executing them in production
