Qwen2.5-1.5B-Instruct-CodeInfused-IQ3

Model Card

By DuoNeural, published under apache-2.0, revision decc7bbff163.

Calibrated with DuoNeural 131k-token code-infused activation Hessian (qwen15gtap.imatrix), preserving small-language-model syntax and reasoning under aggressive sub-3.5-bit compression. G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics: 1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing. 2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line. 3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

Read DuoNeural's full model card

[!NOTE] Experimental Release: Pending Further Verification / Empirical Validation
This checkpoint was produced by the DuoNeural Research Lab exploring Generalized Thouless-Anderson-Palmer (G-TAP v3) statistical mechanics post-training quantization on edge architectures.

Key Metrics (Measured on RTX 4080 Super 32GB Pod)

Precision / BPW	Model Footprint	Holdout Perplexity (131k tokens)	GSM8K Math CoT	Python Code AST (15 Tests)	Hermes Tool Calling	Decode Throughput
~3.2 bpw	0.62 GiB (635 MB)	3.1835	18/25 (72.0%)	8/15 (53.3%)	15/15 (100.0%)	249.6 t/s

Architectural & Theoretical Context

Calibrated with DuoNeural 131k-token code-infused activation Hessian (qwen15_gtap.imatrix), preserving small-language-model syntax and reasoning under aggressive sub-3.5-bit compression.

What is G-TAP v3?

G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics: 1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing. 2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line. 3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

Quickstart

# Run with llama-cli
llama-cli -hf DuoNeural/Qwen2.5-1.5B-Instruct-CodeInfused-IQ3_XXS-GGUF -p "def fibonacci(n):" -n 256

# Serve with llama-server
llama-server -hf DuoNeural/Qwen2.5-1.5B-Instruct-CodeInfused-IQ3_XXS-GGUF -c 4096 -ngl 99 --port 8080

DuoNeural Cognitive Light Cone — Jesse Caldwell, Archon, Aura
Empirically Validated on NVIDIA RTX 4080 Super 32GB Pod Testbed

Identity and Version

Repository: DuoNeural/Qwen2.5-1.5B-Instruct-CodeInfused-IQ3_XXS-GGUF
Publisher: DuoNeural
Task: Text generation
Modality: Text
Library: transformers
Parameters: Not stated by the source
Languages: en
Revision: decc7bbff163352aa6dcdf862bfee2aa47307978
First published: 2026-09-29
Last updated: 2026-09-29

Files and Weights

3 files, 668.8 MB in total. The weights are 1 file totalling 668.8 MB in gguf.

Weights1 file · 668.8 MB

Documentation1 file · 2.2 KB

Repository1 file · 1.6 KB

Every file

File	Type	Size	SHA-256
Qwen2.5-1.5B-Instruct-CodeInfused-IQ3_XXS.gguf	Weights	668.8 MB	b83034d97ef1
README.md	Documentation	2.2 KB	—
.gitattributes	Repository	1.6 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 668.8 MB

Download from DuoNeural

Released by DuoNeural through its official repository on Hugging Face. Read the license.

Built From

Derived from Qwen/Qwen2.5-1.5B-Instruct
Quantized from Qwen/Qwen2.5-1.5B-Instruct

Memory Requirements

Precision	Weights in memory
As published	668.8 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Qwen2.5-1.5B-Instruct-CodeInfused-IQ3_XXS-GGUF

Can I use Qwen2.5-1.5B-Instruct-CodeInfused-IQ3_XXS-GGUF commercially?

Yes. Qwen2.5-1.5B-Instruct-CodeInfused-IQ3_XXS-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

View model

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

View model

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

View model

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

View model

Model · Text generation

Qwen3.8-27B-Uncensored-GGUF

Jonathan Coletti

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp

View model

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers

View model