---

license: mit

base_model: ornith-ai/Ornith-1.5-35B-A3B

base_model_relation: quantized

pipeline_tag: image-text-to-text

library_name: gguf

datasets:

• NousResearch/hermes-function-calling-v1

language:

- en

- zh

- multilingual

tags:

- gguf

- llama.cpp

- qwen35moe

- moe

- imatrix

- unsloth-dynamic

- agentic-coding

- token-efficient

- vision

- genesis

- hermes

---

🌟 Tiel-Coder-35B-A3B-GGUF -> Genesis Hermes

> ⚡ https://web.tribute.tg/d/KIH ⚡ If you like this Genesis LLM release you can donate to me via @Tribute bot in Telegram messenger and support future Genesis LLM development.

> ⚡ Why Genesis project exists? During training, ALL models don't just learn knowledge - they also accumulate random noise in their tensors. This noise builds up and creates something I call the Noise Gate - a fundamental barrier that stops LLM models from learning further and makes them unstable, verbose, and prone to hallucinations. My approach reduces this noise. It repairs the signal in tensors without touching the learned knowledge and gradient using Marchenko–Pastur distribution as a core criteria. The result is a model that consistent in performance, context clarity and following instructions, because it's no longer fighting its own internal chaos.

> What is Genesis? Genesis is post training data regeneration and calibrarion algorythm for neural networks (LLM) in GGUF format that I made with AI help during almost half a year of development. It's optimized, architecture independent, works with any model in GGUF format and based on mathematical statistics. I don't train or finetune models, I repair purity of signal in them instead on Google Collab Free on Tesla T4 GPU via Python based on how models learns information. On first stage I scan ssm_conv1d tensors in model, they handle long context memory. I repair balance between heads in them. On second stage, I scan blocks in model via chunks via 3 parameters and pick best one that fits to weight distribution in tensor. Best picked chunk replaces zero chunks in broken tensor without touching learned structure in model. On third stage I scan model and detect noise in tensors via custom SVD. During scanning I exclude token_embd.weight, output.weight, 1D tensors, bias and norms. Then I reduce training noise in tensors via custom SVD based on Marchenko–Pastur law with preserved training data, 99% of siginal and learned gradient.

Any questions?

> Contact: luffythefox@mail.ru, azakharchenko92@gmail.com

> My Telegram: @LuffyTheFox

Model is based on peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF base.

And DJLougen/hermes-qwen3.5-35b-a3b-GGUF finetune for Hermes agent.

I transferred data from finetune on Hermes dataset (around 2k blocks from two FFN expert tensors) to peculiar-ragdoll base. And processed model via Genesis.

> Join the Discord for updates, roadmaps, projects, or just to chat.

Base model. peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF

Thanks to peculiar-ragdoll

Tensor repair by me. Method: Genesis

Links:

• Original model
• Quantization Script with Unsloth profiles support

---

</details>

LLM models often have:

• Saturated weights: the model's activations are stuck, gradients vanish, outputs degrade.
• Scale mismatches: one layer's weights are 10× larger than its peers for no good reason.
• Mean drift: weight distributions shifted positive or negative, breaking symmetry assumptions.
• Zero blocks: zero blocks corrupt the signal, turning training into noise amplification.
• Training Noise: training noise increase randomness and ruins model output quality.

My approach fixes all of that without retraining - pure numerical surgery on the raw bytes of the file.

Quantization script available here: https://pastebin.com/hXhcMJn9

Feel free to do your own quants if you want.

Recommended Settings for best perfomance on APEX quant

Set K Cache Quantization Type and V Cache Quantization Type to F16.

Set Number of layers for which to force MoE weights onto CPU to 40.

Set GPU offload to maximum. Set number of active experts to 8.

Thinking mode (coding):

• Hermes agent: temperature=0.6, top_p=1.0, top_k=20, min_p=0.0, seed=42, presence_penalty=disabled, repeat_penalty=1.05
• Coding/precise tasks: temperature=0.6, top_p=1.0, top_k=20, min_p=0.0, seed=42, presence_penalty=disabled, repeat_penalty=disabled
• General: temperature=1.0, top_p=0.0, top_k=20, min_p=1.0, seed=42, presence_penalty=disabled, repeat_penalty=disabled

Non Thinking mode (creative):

• General: temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, seed=42, presence_penalty=disabled, repeat_penalty=disabled

Usage

Ready to use. Recommended quant: NVFP4

Available here: Tiel-Coder-35B-A3B-Genesis-Hermes-NVFP4-GGUF

Important:

• Keep at least 128K context to preserve thinking capabilities
• Use --jinja flag with llama.cpp for proper chat template handling
• Vision support requires the mmproj file alongside the main GGUF

---

Specs

• 35B total parameters, ~3B active per forward pass (MoE)
• 256 experts, 8 routed + 1 shared per token
• Hybrid architecture: Gated DeltaNet linear attention + full softmax attention (3:1 ratio)
• 40 layers, pattern: 10 × (3 × DeltaNet-MoE + 1 × Attention-MoE)
• 262K native context (extendable to 1M with YaRN)
• Natively multimodal (text, image, video)
• 248K vocabulary, 201 languages
• Base model. peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF

---

Compatibility

Works with llama.cpp, LM Studio, koboldcpp, and other GGUF-compatible runtimes.