Downloads · 30 days
59
5% of all-time downloads
caiovicentino1/Gemma-4-31B-Claude-Opus-HLWQ-Q5-Vision
Gemma-4-31B-Claude-Opus-HLWQ-Q5-Vision is a image-text-to-text model from caiovicentino1. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
[!IMPORTANT] Naming notice (2026-04-10). The "HLWQ" technique used in this model is being rebranded to HLWQ (Hadamard-Lloyd Weight Quantization). The change is only the name; the algorithm and the weights in this repo…
Downloads · 30 days
59
5% of all-time downloads
All-time downloads
1.2K
Public
Repo size
21.9 GB
Likes
18
Public
Click a slice to open those files.
.pt21.8 GB · 100%
From the Hugging Face model README
[!IMPORTANT] Naming notice (2026-04-10). The "HLWQ" technique used in this model is being rebranded to HLWQ (Hadamard-Lloyd Weight Quantization). The change is only the name; the algorithm and the weights in this repository are unchanged.
The rebrand resolves a name collision with an unrelated, earlier KV cache quantization method also named HLWQ (Han et al., arXiv:2502.02617, 2025). HLWQ addresses weight quantization with a deterministic Walsh-Hadamard rotation and Lloyd-Max scalar codebook; Han et al.'s HLWQ addresses KV cache quantization with a random polar rotation. The two methods are technically distinct.
Existing loaders that load this repository by ID continue to work without changes. Future model uploads will use the HLWQ name.
Reference paper for this technique: arXiv:2603.29078 (v2 in preparation; v1 still uses the old name).
Claude Opus distilled Gemma 4 31B + Vision on consumer GPUs.
Download: 21.8 GB (vs 62.5 GB BF16 — 2.9x compression)
| Component | Method | Result |
|---|---|---|
| Text weights | HLWQ Q5 + torchao INT4 | 21.8 GB |
| Vision encoder | BF16 (full quality) | included |
| KV Cache | HLWQ Q3 (5.3x) | longer context |
| Reasoning | Claude Opus 4.6 distilled | high-effort |
| Metric | Value |
|---|---|
| VRAM | 22.8 GB (streaming loader) |
| Speed | ~24.9 tok/s |
| Download | 21.8 GB |
| Vision | ✅ Golden Gate Bridge |
| Compression | 2.9x |
| Quantized layers | 602 |

| GPU | VRAM | Fits? |
|---|---|---|
| RTX 4090 | 24 GB | ✅ |
| L4 | 24 GB | ✅ |
| RTX 5090 | 32 GB | ✅ |
| A100 | 40-80 GB | ✅ |
pip install polarquant[all]
polarquant chat TeichAI/gemma-4-31B-it-Claude-Opus-Distill --vision
| Method | Bits | Compression | Max Context (4GB) |
|---|---|---|---|
| FP16 | 16 | 1.0x | 4K |
| HLWQ Q4 | 4 | 4.0x | 17K |
| HLWQ Q3 | 3 | 5.3x | 22K |
| HLWQ Q2 | 2 | 8.0x | 35K |
@article{polarquant2025,
title={HLWQ: Hadamard-Rotated Lloyd-Max Quantization for LLM Compression},
author={Vicentino, Caio},
journal={arXiv preprint arXiv:2603.29078},
year={2025}
}
pip install git+https://github.com/caiovicentino/polarengine-vllm.git
from polarengine_vllm import HLWQModel
model = HLWQModel.from_pretrained("caiovicentino1/Gemma-4-31B-Claude-Opus-HLWQ-Q5-Vision")
print(model.generate("Hello, how are you?", max_new_tokens=100))
model = HLWQModel.from_pretrained("caiovicentino1/Gemma-4-31B-Claude-Opus-HLWQ-Q5-Vision", kv_cache_nbits=3)
# KV cache now uses 5.3x less memory — fit longer conversations!
print(model.generate("Explain quantum computing in detail.", max_new_tokens=500))
polarquant bench caiovicentino1/Gemma-4-31B-Claude-Opus-HLWQ-Q5-Vision --ppl --chart
polarquant demo caiovicentino1/Gemma-4-31B-Claude-Opus-HLWQ-Q5-Vision --share
Hadamard Rotation + Lloyd-Max Optimal Centroids
Unlike GGUF (uniform quantization), HLWQ places quantization levels where weight density is highest — mathematically proven optimal for Gaussian-distributed neural network weights.
HLWQ Q5 (cos_sim > 0.996) > GGUF Q5_K_M (~0.99) at same size