OR

RegesCore 1.0 35

OrnithGGUF by iBossonlineUpdated 2026-10-11
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant10.5 GB
Quick answer

RegesCore 1.0 35 needs about 23.3 GB of memory at Q4_K_M (a 22.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 10.5 GB (IQ1_S) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

RegesCore 1.0 35: 35B Mixture‑of‑Experts model for coding and infrastructure tasks

RegesCore 1.0 35 is a 35‑billion‑parameter mixture‑of‑experts model based on Ornith‑1.0‑35B. It is optimized for agentic coding, Linux and infrastructure operations, security tooling, and Lua game‑server scripting. The model is MIT licensed and runs on local hardware via llama.cpp, LM Studio, or Ollama.

Good at

  • Agentic coding with multi‑file edits
  • Linux and infrastructure automation
  • Security and reverse‑engineering support

Limits

  • Requires a system prompt for best results
  • No vision support
  • Large memory footprint for full‑precision quantization

Best for

  • Developing secure infrastructure scripts
  • Automating Linux system tasks
  • Building Lua game‑server logic

Who it’s for. Engineers and security professionals who need a local, open‑source LLM for coding, system automation, and reverse‑engineering. The model is suitable for private deployments where data must not leave the local environment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S10.5 GB 11.7 GB
Too big Get file →
IQ1_M11.0 GB 12.2 GB
Too big Get file →
IQ2_XXS11.5 GB 12.7 GB
Too big Get file →
IQ2_M11.6 GB 12.7 GB
Too big Get file →
Q2_K_XL12.3 GB 13.4 GB
Too big Get file →
IQ3_XXS13.7 GB 14.9 GB
Too big Get file →
IQ3_S15.0 GB 16.2 GB
Too big Get file →
Q3_K_M16.7 GB 17.9 GB
Too big Get file →
Q3_K_XL16.8 GB 18.0 GB
Too big Get file →
IQ4_XS17.8 GB 19.0 GB
Too big Get file →
IQ4_NL18.1 GB 19.3 GB
Too big Get file →
Q4_K_S20.9 GB 22.1 GB
Too big Get file →
MXFP4_MOE21.7 GB 22.8 GB
Too big Get file →
Q4_K_M22.1 GB 23.3 GB
Too big Get file →
Q4_K_XL22.3 GB 23.5 GB
Too big Get file →
Q5_K_S24.9 GB 26.1 GB
Too big Get file →
Q5_K_M26.5 GB 27.6 GB
Too big Get file →
Q5_K_XL26.5 GB 27.7 GB
Too big Get file →
Q6_K29.3 GB 30.5 GB
Too big Get file →
Q6_K_XL31.8 GB 33.0 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →
Q8_K_XL38.2 GB 39.4 GB
Too big Get file →
BF1669.4 GB (2 parts) 70.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (10.52 GB) or IQ1_M (11.04 GB). For 12 GB VRAM, IQ2_XXS or IQ2_M (≈11.5 GB). For 16 GB VRAM, Q3_K_M (≈16.68 GB) or Q4_K_S (≈20.89 GB). Larger VRAM allows higher‑quality quants such as Q5_K_XL or Q6_K_XL.

What GPU do you need for RegesCore 1.0 35?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ1_S (10.5 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.7 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_XL (22.3 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.3 GB file, about 30.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K_XL (38.2 GB file, about 39.4 GB in use).

Which RegesCore 1.0 35 quant should you choose?

Q4_K_M is the usual starting point for RegesCore 1.0 35: it balances file size and quality well. Here it is a 22.1 GB file.

The Q8_0 file is 36.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 10.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized byiBossonline
FamilyOrnith
Licensemit
Downloads (HF)6,089
Last updated2026-10-11

Frequently asked questions about RegesCore 1.0 35

How much VRAM does RegesCore 1.0 35 need?

About 23.3 GB at Q4_K_M with an 8K context window. That is the 22.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run RegesCore 1.0 35 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of RegesCore 1.0 35 GGUF?

It depends on the quant: IQ1_S is 10.5 GB, IQ1_M is 11.0 GB, IQ2_XXS is 11.5 GB, IQ2_M is 11.6 GB, Q2_K_XL is 12.3 GB, IQ3_XXS is 13.7 GB and 17 more.

What context length does RegesCore 1.0 35 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download RegesCore 1.0 35 GGUF?

The files are on Hugging Face in the iBossonline/RegesCore-1.0-35 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does RegesCore 1.0 35 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run RegesCore 1.0 35 on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantization. The estimated VRAM usage is about 11.7 GB at 8k context.

Does the model support vision?

No, RegesCore 1.0 35 does not have vision capabilities.

Is the model fine‑tuned for security tasks?

No, the model is not fine‑tuned; it relies on system prompts for security use cases.

Other GGUFs of Ornith-1.0-35B

Similar models

Browse all →

More from iBossonline

All by iBossonline →

More Ornith models

All Ornith →

Other large models

All large models →