Downloads · 30 days
7
11% of all-time downloads
mozarcik/Llama-PLLuM-8B-chat-2512-awq
Llama-PLLuM-8B-chat-2512-awq is a text generation model from mozarcik. Use it when you need the model to write or continue text. It is set up for vllm. The card lists the license as llama3.1.
Built with Llama. AWQ W4A16 quantization of CYFRAGOVPL/Llama-PLLuM-8B-chat-2512 for single-GPU vLLM deployment on consumer/prosumer hardware. Validated on 1× AMD Radeon AI PRO R9700 (gfx1201, TP=1); the compressed-ten…
Downloads · 30 days
7
11% of all-time downloads
All-time downloads
62
Public
Parameters
2B
5.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.7 GB · 100%
How the weights are stored.
I327B · 86%
From the Hugging Face model README
Built with Llama. AWQ W4A16 quantization of CYFRAGOVPL/Llama-PLLuM-8B-chat-2512 for single-GPU vLLM deployment on consumer/prosumer hardware. Validated on 1× AMD Radeon AI PRO R9700 (gfx1201, TP=1); the compressed-tensors format is expected to be portable to NVIDIA via awq_marlin — not independently validated in this release.
Kwantyzacja AWQ W4A16 modelu Llama-PLLuM-8B-chat-2512 — uruchamia się na pojedynczej konsumenckiej karcie AMD Radeon AI PRO R9700 (32 GB VRAM) przez vLLM. Część Run-3 (rozszerzenie rodziny PLLuM AWQ poza 70B na desktop/laptop tier).
⚠ Note on Hugging Face parameter display: Hugging Face may show this quantized repository with reduced parameter count because the safetensors index counts packed 4-bit tensors. The logical base architecture is Llama-PLLuM-8B (8.03B parameters); this repository contains AWQ-compressed derivative weights of the 8B model. Verify with the base model card:
CYFRAGOVPL/Llama-PLLuM-8B-chat-2512.
Czterobitowa kwantyzacja (AWQ W4A16, format compressed-tensors) modelu Llama-PLLuM-8B-chat-2512 wytworzonego przez konsorcjum PLLuM (SpeakLeash, OPI-PIB, NASK, Politechnika Wrocławska), publikowanego na HuggingFace przez Ministerstwo Cyfryzacji RP (organizacja CYFRAGOVPL). Celem kwantyzacji jest deployment na pojedynczej karcie konsumenckiej — 5.53 GiB footprintu pozwala uruchomić 8B parametrów na 1× AMD Radeon AI PRO R9700 (32 GB VRAM) z dużym headroomem dla KV cache (22.22 GiB available, max_concurrency 88.89× przy max_seq_len=2048).
Dla kogo:
Co dało nowego: według wiedzy autora — pierwsza publiczna kwantyzacja AWQ W4A16 (vLLM-native compressed-tensors) tego wariantu Llama-PLLuM-8B (stan na 2026-05-26). Dla użytkowników llama.cpp/ollama dostępne są GGUF quantizacje społeczności; tutejsze wagi są zoptymalizowane pod inferencję serwerową w vLLM.
4-bit AWQ W4A16 quantization (compressed-tensors format) of Llama-PLLuM-8B-chat-2512 developed by the PLLuM consortium (SpeakLeash, OPI-PIB, NASK, Wrocław University of Science and Technology), published on HuggingFace by the Polish Ministry of Digital Affairs (CYFRAGOVPL). Quantized for single-GPU consumer deployment: 5.53 GiB footprint fits comfortably on a single 32 GB R9700 with large KV cache headroom (22.22 GiB → 88.89× concurrency at max_seq_len=2048), served via vLLM. To the author's knowledge, this is the first public AWQ W4A16 (vLLM-native compressed-tensors) quantization of this Llama-PLLuM-8B-chat-2512 checkpoint (HuggingFace Hub check, 2026-05-26).
| Parameter | Value |
|---|---|
| Method | AWQ W4A16 (activation-aware) |
| Library | llm-compressor |
| Format | compressed-tensors (vLLM-native) |
| Group size | 128 |
| Bits / weights | 4 |
| Bits / activations | 16 (bf16) |
| Calibration host | AMD Radeon AI PRO R9700 (gfx1201, RDNA 4), local workstation — 2× R9700 (64 GB VRAM combined), Ryzen 9 9950X3D, Kubuntu 24.04, ROCm 7.2.1 |
| Calibration corpus | mozarcik/clinical-pl-smpc-awq-calibration — 418 chunks (~512 tokens) polskich Charakterystyk Produktów Leczniczych (SmPC) z EMA; pulmonologia + onkologia klatki piersiowej; No PHI |
| Skipped layers | lm_head (standard) |
| Recipe | AWQModifier(scheme="W4A16", targets="Linear", ignore=["lm_head"]) — patrz recipe.yaml w repo |
Pełna procedura kwantyzacji + skrypty: navimed-umb/calibration/quantization/.
Pomiary z weryfikacji vehicle-integrity (METHODOLOGY §8) na 1× AMD Radeon AI PRO R9700 (gfx1201), TP=1, max_seq_len=2048, enforce_eager=True:
| Metric | Value |
|---|---|
| Footprint (model weights) | 5.53 GiB |
| KV cache available | 22.22 GiB |
| Maximum concurrency @ 2048 tok/req | 88.89× |
| Init engine time | 3.56 s |
| vLLM ready time (from cold start) | ~30 s |
| Sanity response time (5 PL prompts, max_tokens=64) | ~6 s/prompt |
Verdict: PASS (5/5 prompts non-empty, coherent Polish output)
Raw outputs: navimed-umb/environment/sanity-tests/2026-05-26-Llama-PLLuM-8B-chat-2512-awq-sanity.json.
Co to znaczy "envelope": to są twarde liczby pamięci/ładowania/pojemności KV — czyli "czy model w ogóle się mieści i odpowiada poprawnie na pojedyncze zapytanie". To nie są liczby throughput (tok/s, P50/P95, scaling z N) — te pozostają EMBARGOED do akceptacji paper'a (METHODOLOGY §11.2, stricter embargo dla modeli polskich §11.3).
5 polskich promptów medycznych (Stolicą Polski / Tiotropium / Astma / Pacjent z dusznością / Spirometria) via /v1/completions, temperature=0.0, max_tokens=64. Vehicle-integrity per METHODOLOGY §8 — NIE ocena jakości modelu.
Verdict: PASS (5/5 coherent Polish output, no degeneration, medical context plausible)
Sample (Tiotropium prompt):
"Tiotropium to lek wziewny stosowany w leczeniu astmy oskrzelowej i przewlekłej obturacyjnej choroby płuc (POChP). Zawiera on substancję czynną tiotropiumbromek, która działa na receptory muskarynowe M3 znajdujące [...]"
Raw outputs: linked above (sanity JSON).
⚠ Important — ignore Hugging Face autogenerated snippets. The "Use this model" button on the HF UI may suggest snippets like
pipeline("text-generation", model="...")or a barevllm serve "..."— these are incomplete for this quantized AWQ release and will fail or misbehave without the flags below (ROCm env vars,--quantization compressed-tensorsorawq_marlin,--enforce-eageron gfx1201).
Stack: vLLM 0.19.0+rocm721 PINNED + ROCm 7.2 + PyTorch 2.10 (regressions reported on newer ROCm wheels on gfx1201, cf. Capitelli #40980). Build wheel from ROCm vLLM fork or use AMD-provided container — NOT available on PyPI. Setup: navimed-umb environment/.
# Required env vars for gfx1201
export VLLM_ROCM_USE_AITER=0 # AITER unsupported on gfx1201
export AMD_SERIALIZE_KERNEL=1
export HIP_LAUNCH_BLOCKING=1
export ROCR_VISIBLE_DEVICES=0 # single GPU; adjust for your card
vllm serve mozarcik/Llama-PLLuM-8B-chat-2512-awq \
--tensor-parallel-size 1 \
--enforce-eager \
--max-model-len 2048 \
--gpu-memory-utilization 0.90 \
--quantization compressed-tensors
vllm serve mozarcik/Llama-PLLuM-8B-chat-2512-awq \
--tensor-parallel-size 1 \
--max-model-len 4096 \
--gpu-memory-utilization 0.85 \
--quantization awq_marlin
Note for NVIDIA users: drop
--enforce-eager(CUDA graphs work on Hopper/Ampere/Ada); useawq_marlinquantization flag (faster on NVIDIA thancompressed-tensors); lowergpu_memory_utilizationto 0.85 to avoid OOM with fragmentation. Ifawq_marlinis rejected by your vLLM version, fall back to--quantization awq.
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "mozarcik/Llama-PLLuM-8B-chat-2512-awq",
"messages": [{"role": "user", "content": "Wyjaśnij krótko zasadę działania spirometrii."}],
"max_tokens": 256,
"temperature": 0.3
}'
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="dummy")
resp = client.chat.completions.create(
model="mozarcik/Llama-PLLuM-8B-chat-2512-awq",
messages=[{"role": "user", "content": "Wyjaśnij krótko zasadę działania spirometrii."}],
max_tokens=256, temperature=0.3,
)
print(resp.choices[0].message.content)
awq_marlin performance jest typowa dla AWQ Marlin kernels (cf. vLLM docs).llm-compressor v_proj skip on GQA — known library artifact dla Grouped-Query Attention (Llama 3.1 family); patrz vllm-project/llm-compressor#issues. Wpływ na koherencję outputu zweryfikowany Gate 2 probe — patrz sekcja powyżej.Research and engineering use only.
Model dialogowy (instrukcja + RLHF). Przeznaczony do interakcji wieloturowych w polskim — asystent research/edukacyjny, prototypowanie chat UX, ewaluacja jakości dialogu. Obsługuje /v1/chat/completions z chat template z tokenizera.
This model is NOT intended for, and is NOT validated for:
The calibration corpus consists of public regulatory text (EMA Summary of Product Characteristics) selected to test Polish-domain robustness and AWQ deployment feasibility — NOT to confer clinical capability. Any clinical application requires independent validation, expert human verification of all output, and appropriate regulatory/ethical clearance.
No clinical guarantee. Not a medical device. Use at your own risk.
This work uses Llama materials. The base model CYFRAGOVPL/Llama-PLLuM-8B-chat-2512 (Llama-PLLuM-8B family by the PLLuM consortium, published by the Polish Ministry of Digital Affairs) is derived from Meta's Llama 3.1 and is governed by the Llama 3.1 Community License Agreement and the Llama 3.1 Acceptable Use Policy.
Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
These quantized derivative weights are redistributed under the same terms; users must comply with both the License and the Acceptable Use Policy.
Base model — Llama-PLLuM-8B family:
CYFRAGOVPLCYFRAGOVPL/Llama-PLLuM-8B-chat-2512Quantization:
mozarcikmozarcik/clinical-pl-smpc-awq-calibration (License: see dataset card; EMA reproduction policy applies)Compute:
0.19.0+rocm721Benchmark suite & methodology:
navimed-umb v0.4.0 — github.com/kicrazom/navimed-umbllama3.1 — inherited from CYFRAGOVPL/Llama-PLLuM-8B-chat-2512.
This repository contains quantized derivative weights only. Use of these weights is subject to:
LICENSE)USE_POLICY.md)NOTICE) reproducing the required Meta copyright text@software{minarowski_2026_pllum8b_chat_2512_awq,
author = {Minarowski, Łukasz},
title = {{Llama-PLLuM-8B-chat-2512} AWQ W4A16 quantization for vLLM on consumer AMD},
year = {2026},
publisher = {HuggingFace},
url = {https://huggingface.co/mozarcik/Llama-PLLuM-8B-chat-2512-awq},
doi = {10.5281/zenodo.19851346}
}
Cite the original PLLuM paper:
@article{kocon2025pllum,
title = {PLLuM: A Family of Polish Large Language Models},
author = {Kocoń, Jan and others},
journal = {arXiv preprint arXiv:2511.03823},
year = {2025}
}
This model card was drafted by Claude (Anthropic) as part of an interactive engineering session with the maintainer (Łukasz Minarowski). The maintainer reviewed, edited, and signed off on all factual claims, hardware envelope numbers, license attributions, and release claims before publication. The AI did not generate, modify, or validate: the quantized model weights, benchmark measurements, calibration data, or the underlying methodology.
Niniejsza karta modelu została zredagowana przez Claude (Anthropic) podczas interaktywnej sesji inżynierskiej z opiekunem repo (Łukasz Minarowski). Opiekun zweryfikował, poprawił i zaaprobował wszystkie twierdzenia faktyczne, liczby z envelope sprzętowego, atrybucje licencyjne i twierdzenia release'owe przed publikacją. AI nie generował, nie modyfikował ani nie walidował: wag modelu, wyników pomiarów, danych kalibracyjnych ani metodologii.