Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model

• URL: http://arxiv.org/abs/2603.04162v2
• Date: Thu, 05 Mar 2026 10:39:41 GMT
• Title: Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model
• Abstract summary: We present Bielik-Q2-Sharp, the first systematic academic evaluation of extreme 2-bit quantization applied to a Polish large language model.<n>We compare six state-of-the-art post-training quantization methods -- QuIP#, SpinQuant+GPTQ, ButterflyQuant, QTIP, VPTQ, and AQLM.<n>Our best variant (QuIP# E8P12) achieves 71.92% across 22 Polish benchmarks versus 72.07% for the IQ2_XXS baseline.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Bielik-Q2-Sharp, the first systematic academic evaluation of extreme 2-bit quantization applied to a Polish large language model. Using Bielik-11B-v2.3-Instruct (11B parameters, Mistral architecture) as our base model, we compare six state-of-the-art post-training quantization methods -- QuIP#, SpinQuant+GPTQ, ButterflyQuant, QTIP, VPTQ, and AQLM -- all calibrated on a Polish-language corpus (CulturaX-PL) with shared Hessian matrices. Our best variant (QuIP# E8P12) achieves 71.92% across 22 Polish benchmarks versus 72.07% for the IQ2_XXS baseline -- within statistical noise, at a modest size premium (3.26 GB vs. ~2.6 GB). On eq_bench, our method scores 47.14 versus 43.53 (+3.6pp), suggesting superior preservation of higher-order reasoning. QTIP achieves the best per-bit efficiency (79.4% MC acc_norm at ~2.4 bpw, 3.27 GB), matching VPTQ's quality at 35% smaller size. We additionally document a MC-generation dissociation phenomenon where rotation-based methods preserve log-likelihood quality but fail catastrophically at autoregressive generation. The entire project was conducted by a single independent researcher on cloud GPUs (vast.ai) within a $285 budget. All models, Hessians, and evaluation logs are publicly available.

Related papers

• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability [57.03393882933515]
  We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and 51B parameters of n-gram embedding tables held off the accelerator.<n>On fourteen pre-training benchmarks the model leads the 397B-A17B predecessor on eight and trails it on the rest by at most 2.6 points, at 1/3 the activated parameters, 1/3 the training tokens, and roughly 1/9 the training FLOPs.
  arXiv  Detail & Related papers  (2026-08-31T06:35:07Z)
• Benchmarking Speech-to-Speech Translation Models [55.00303727199927]
  Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol.<n>We introduce a benchmarking framework integrating 46 metrics across eight dimensions.<n>We deploy it on 1,248 model-language configurations from FLEURS and CVSS.
  arXiv  Detail & Related papers  (2026-06-02T07:01:33Z)
• Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluation [1.2891210250935148]
  We package Microsoft's QuantumKatas quantum computing curriculum with an evaluation framework for systematic LLM assessment.<n>The resulting benchmark comprises 350 tasks across 26 categories, spanning fundamental gates through advanced algorithms.<n>Each task includes a natural language prompt, canonical solution, and deterministic test verification via classical circuit simulation.
  arXiv  Detail & Related papers  (2026-05-26T16:02:08Z)
• Adapting Large Language Models to a Low-Resource Agglutinative Language: A Comparative Study of LoRA and QLoRA for Bashkir [0.0]
  This paper presents a comparative study of parameter-efficient fine-tuning methods, including LoRA and QLoRA, applied to the task of adapting large language models to the Bashkir language.<n> Experimental evaluation is conducted on a Bashkir text corpus of 71k documents (46.9M tokens) using models of various architectures.
  arXiv  Detail & Related papers  (2026-05-06T14:14:35Z)
• Democratizing AI with Small Language Models: Structured Benchmarking and Parameter-Efficient Fine-Tuning for Local Deployment [0.0]
  We evaluate nine open-weight language models between 135M and 3B parameters on a benchmark designed for structured local deployment.<n>A shared parameter-efficient fine-tuning pipeline adapts a subset of models using 4-bit NF4 quantization with DoRA/LoRA-style adapters on an NVIDIA L4-class budget.<n>In base evaluation, Qwen Coder 3B leads at 75.67% strict accuracy, followed by Qwen2.5 1.5B at 67.10%, Qwen3.5 2B at 64.98%, and Granite 3.3 2B at 64.61%.
  arXiv  Detail & Related papers  (2026-05-05T02:36:09Z)
• Gemma 4, Phi-4, and Qwen3: Accuracy-Efficiency Tradeoffs in Dense and MoE Reasoning Language Models [6.396911723204044]
  Mixture-of-experts (MoE) language models are often expected to offer better quality-efficiency tradeoffs than dense models.<n>We present a benchmark of seven recent reasoning-oriented instruction-tuned models spanning dense and MoE designs.
  arXiv  Detail & Related papers  (2026-04-08T12:50:52Z)
• Efficient Fine-Tuning Methods for Portuguese Question Answering: A Comparative Study of PEFT on BERTimbau and Exploratory Evaluation of Generative LLMs [1.5049442691806052]
  This work presents a systematic evaluation of BERTimbau for Question Answering on SQuAD-BR, the Brazilian Portuguese translation of SQuAD v1.<n>We show that encoder-based models can be efficiently fine-tuned for extractive Brazilian Portuguese QA with substantially lower computational cost than large generative LLMs.
  arXiv  Detail & Related papers  (2026-03-22T21:56:05Z)
• Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem Routing [0.0]
  Chain of Simulation (CoS) is a novel dual-mode reasoning framework that dynamically routes problems to specialized reasoning strategies.<n>CoS employs three distinct reasoning modes: computational flow with self-consistency for mathematical problems, symbolic state tracking with representations for spatial reasoning, and hybrid fact-extraction for multi-hop inference.
  arXiv  Detail & Related papers  (2026-02-02T21:44:01Z)
• Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought [23.847410628315544]
  We introduce **Language-Mixed CoT**, a reasoning schema that switches between English and a target language.<n>We train ninve models (4B-35B) across six families (Qwen2.5, Llama-3.1, Gemma-3, etc)<n>Our best model, **KO-REAson-35B**, achieves state-of-the-art performance, with the highest overall average score (64.0 pm 25)
  arXiv  Detail & Related papers  (2025-10-05T14:39:41Z)
• Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models [4.238165821317982]
  LieQ is a metric-driven framework that addresses the challenge of maintaining accuracy in sub-7B models under extreme low-bit compression.<n>Our method introduces three complementary layer-wise diagnostics-Perplexity Drop, Representational Compactness, and Top-k Energy Gain.<n>On Qwen3-4B, LieQ recovers 95.9% of FP16 baseline performance at 2.05-bit quantization, outperforming GPTQ by 19.7% and AWQ by 18.1% on average across seven zero-shot reasoning tasks.
  arXiv  Detail & Related papers  (2025-08-05T11:17:04Z)
• Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression [55.323397702682506]
  Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining.<n>We develop a new mixed-precision PTQ approach, Task-Circuit Quantization (TaCQ), that draws parallels to automated circuit discovery.
  arXiv  Detail & Related papers  (2025-04-10T02:19:03Z)
• S*: Test Time Scaling for Code Generation [55.11863577956177]
  We propose S*, the first hybrid test-time scaling framework for code generation.<n>S* substantially improves the coverage and selection accuracy of generated code.
  arXiv  Detail & Related papers  (2025-02-20T09:18:53Z)
• Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis [89.60263788590893]
  Post-training Quantization (PTQ) technique has been extensively adopted for large language models (LLMs) compression.<n>Existing algorithms focus primarily on performance, overlooking the trade-off among model size, performance, and quantization bitwidth.<n>We provide a novel benchmark for LLMs PTQ in this paper.
  arXiv  Detail & Related papers  (2025-02-18T07:35:35Z)
• Preference Optimization for Reasoning with Pseudo Feedback [100.62603571434167]
  We introduce a novel approach to generate pseudo feedback for reasoning tasks by framing the labeling of solutions as an evaluation against associated test cases.<n>We conduct experiments on both mathematical reasoning and coding tasks using pseudo feedback for preference optimization, and observe improvements across both tasks.
  arXiv  Detail & Related papers  (2024-11-25T12:44:02Z)
• VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models [11.708250566573334]
  We introduce Vector Post-Training Quantization (VPTQ) for extremely low-bit quantization of Large Language Models (LLMs) VPTQ reduces model quantization perplexity by $0.01$-$0.34$ on LLaMA-2, $0.38$-$0.68$ on Mistral-7B, $4.41$-$7.34$ on LLaMA-3 over SOTA at 2-bit. We also extend VPTQ to support residual and outlier quantization, which enhances model accuracy and further compresses the model.
  arXiv  Detail & Related papers  (2024-09-25T16:25:45Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• Common 7B Language Models Already Possess Strong Math Capabilities [61.61442513067561]
  This paper shows that the LLaMA-2 7B model with common pre-training already exhibits strong mathematical abilities. The potential for extensive scaling is constrained by the scarcity of publicly available math questions.
  arXiv  Detail & Related papers  (2024-03-07T18:00:40Z)
• APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models [12.006605064782567]
  We propose APTQ (Attention-aware Post-Training Mixed-Precision Quantization) for Large Language Models. We leverage the Hessian trace as a sensitivity metric for mixed-precision quantization, ensuring an informed precision reduction. Experiments show APTQ surpasses previous quantization methods, achieving an average of 4 bit width a 5.22 perplexity.
  arXiv  Detail & Related papers  (2024-02-21T07:45:22Z)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.