Leanstral-RotorQuant

KV-cache quantized Leanstral-2603 using RotorQuant for high-throughput Lean 4 formal proof generation.

Leanstral is the first open-source AI agent purpose-built for Lean 4 formal proofs -- generating both executable code and machine-checkable mathematical proofs. This variant applies RotorQuant KV-cache quantization, delivering 5.3x faster prefill and 28% faster decode compared to TurboQuant while preserving full BF16 model weights.

Overview

This repository provides the RotorQuant KV-cache-only configuration of Leanstral-2603. The model weights remain at full precision; only the KV cache is quantized during inference using RotorQuant's rotation-aware quantization scheme.

Spec	Value
Base model	mistralai/Leanstral-2603
Architecture	Mistral MoE (~119B parameters, 7 consolidated shards)
Compression	RotorQuant KV-cache quantization
Weight precision	BF16 (unmodified)
KV-cache precision	Mixed-precision quantized
Prefill speedup	5.3x vs TurboQuant
Decode speedup	28% vs TurboQuant
License	Apache 2.0
Use case	Lean 4 formal verification, theorem proving, mathematical proofs

Quickstart

from transformers import AutoModelForCausalLM, AutoTokenizer
from turboquant import IsoQuantCache

model_id = "majentik/Leanstral-RotorQuant"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)

# Enable RotorQuant KV-cache quantization
cache = IsoQuantCache(model)

prompt = "Prove that for all natural numbers n, n + 0 = n in Lean 4:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    past_key_values=cache,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

What is RotorQuant?

RotorQuant is an advanced KV-cache quantization method that leverages rotation-aware quantization to achieve superior throughput compared to standard KV-cache compression. By exploiting the rotary positional embedding structure, RotorQuant achieves:

• 5.3x faster prefill -- critical for long Lean 4 proof contexts
• 28% faster decode -- faster token-by-token proof generation
• Equivalent memory savings to TurboQuant with better computational efficiency

This makes RotorQuant the preferred choice for interactive theorem proving sessions where latency matters.

Memory Estimates

Component	Estimate
Model weights (BF16)	~238 GB
KV-cache savings	2-4x reduction vs FP16 KV cache
Recommended VRAM	4x A100 80GB or equivalent

Lean 4 Use Case

Leanstral excels at:

• Formal verification -- generating machine-checkable proofs of mathematical theorems
• Theorem proving -- interactive and automated proof search in Lean 4
• Code generation -- writing verified Lean 4 programs with correctness guarantees
• Proof repair -- fixing incomplete or broken proof scripts

See Also

• mistralai/Leanstral-2603 -- Base model
• majentik/Leanstral-TurboQuant -- TurboQuant KV-cache variant
• majentik/Leanstral-RotorQuant-MLX-4bit -- MLX 4-bit + RotorQuant
• majentik/Leanstral-RotorQuant-MLX-2bit -- MLX 2-bit + RotorQuant
• majentik/Leanstral-RotorQuant-MLX-1bit -- MLX 1-bit + RotorQuant
• RotorQuant repository