RL-Quantum-4B-GGUF

QUASAR is a 4B-parameter language model fine-tuned from Qwen3-4B-Instruct-2507 through supervised learning followed by agentic reinforcement learning with tool-augmented feedback. Specially designed for generating OpenQASM 3.0 quantum circuits for tasks like QAOA and VQE, the model optimizes for both syntactic validity and semantic fidelity, using external quantum simulation for reward calculation across hierarchical criteria (syntax, distribution alignment, expectation value, and optimization progress). QUASAR is best suited for natural language to quantum circuit generation and quantum optimization algorithm design in research or integration scenarios, though users are advised to validate its outputs using external quantum simulators to address limitations in problem generalization. Training used a dataset with QASM 3.0 circuits and quantum optimization problems, employing SFT and RL (with GRPO and hierarchical reward). In evaluations, the model substantially outperforms comparable baselines—achieving leading results in syntactic correctness, distributional alignment, expectation-value matching, and high-quality circuit yield in both Pass@1 and Pass@10 metrics.

Model Files

File Name	Quant Type	File Size
rl_quantum_4b.BF16.gguf	BF16	8.05 GB
rl_quantum_4b.F16.gguf	F16	8.05 GB
rl_quantum_4b.F32.gguf	F32	16.1 GB
rl_quantum_4b.Q2_K.gguf	Q2_K	1.67 GB
rl_quantum_4b.Q3_K_L.gguf	Q3_K_L	2.24 GB
rl_quantum_4b.Q3_K_M.gguf	Q3_K_M	2.08 GB
rl_quantum_4b.Q3_K_S.gguf	Q3_K_S	1.89 GB
rl_quantum_4b.Q4_K_M.gguf	Q4_K_M	2.5 GB
rl_quantum_4b.Q4_K_S.gguf	Q4_K_S	2.38 GB
rl_quantum_4b.Q5_K_M.gguf	Q5_K_M	2.89 GB
rl_quantum_4b.Q5_K_S.gguf	Q5_K_S	2.82 GB
rl_quantum_4b.Q6_K.gguf	Q6_K	3.31 GB
rl_quantum_4b.Q8_0.gguf	Q8_0	4.28 GB

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):