estimate, except measured file sizes

Can I run OrcaCyber Nano 1.0 locally?

27B parameters. Parameter count is the published figure.

Licence:: Other (custom, not stated publicly) source
Context:: 262,144 tokens
Modality:: text + image/video in, text out
Released:: 18 Oct 2026 source

What it is

OrcaRouter's dense 27B vision-language model for defensive security work (reverse engineering, vulnerability analysis, secure code review, triage). Ships only as GGUF. The card says: "Loads in stock llama.cpp — no custom kernels". Text, image and video in, text out. Context 262,144. Hugging Face metadata says license: other, and the download is gated (accept the terms; auto-approval). No licence text is public. That is not Apache, MIT, or a Qwen licence. The card does not name the pretrained base. Do not read the Qwen3.5-shaped stack as a claim that this is a Qwen fine-tune. Architecture on the card: Qwen3_5ForConditionalGeneration, 64 layers, hidden size 5120, 48 linear-attention layers and 16 full-attention layers. KV heads (4) and head dim (256) are not on the card; the config is gated. Those two figures are assumed from the Qwen3.5-27B config, which has the same 64 layers, hidden size 5120 and full_attention_interval 4. KV dims assumed from Qwen3.5-27B architecture; OrcaCyber config is gated. Linear-attention layers are stored with a sliding window of 0 so this formula gives them no token KV. The KV figure uses only the 16 full-attention layers and is an estimate. Mix-15.7G is 15.70 GB and Mix-13G is 12.99 GB (decimal GB, Hugging Face file listing, 18 Oct 2026). About 4.65 and 3.85 bits per weight, estimated from 27B parameters. Vendor custom mixes, not Q4_K_M. The memory table does not include the vision projector or the drafter: +0.93 GB vision projector (mmproj F16) for image input; +2.06 GB optional DFlash2 drafter. The card says Mix-13G "fits a 16 GB card with the MTP drafter" and points Mix-15.7G at a "24 GB+ card". That is the vendor's guidance, not this site's fit score. An MTP head is built into both main files. Not in the Ollama library on 18 Oct 2026. Vendor-reported, unverified: AIME 2025 96.23% and MATH-500 98.60%. The card says the evaluation harness is being finalized.

Parameter source · Architecture source · Model page

Memory per quant

KV is at 8,192 tokens. Overhead is 0.8 GB. Both are estimates. A measured file size is labelled. The last column is the cheapest machine that fits the total fully.

Memory per quant for OrcaCyber Nano 1.0
Quant	File size	KV at 8K	+0.8 overhead	Total	Cheapest full fit
Mix-15.7G	15.7 GB measured GGUF	0.5 GB est.	0.8 GB est.	17.0 GB est.	GeForce RTX 3090 24GB, €1,224 (used (median of sold listings))
Mix-13G	13.0 GB measured GGUF	0.5 GB est.	0.8 GB est.	14.3 GB est.	Radeon RX 9060 XT 16GB, €564 (new (lowest in-stock DE board))

Cheapest rig that fits

Mix-15.7G, full: GeForce RTX 3090 24GB, €1,224 (used (median of sold listings))

Mix-15.7G, slow, partly in system RAM: Budget PC with RTX 3060 12GB, slow, partly in system RAM, €1,357 (estimate)

Mix-13G (smallest file), full: Radeon RX 9060 XT 16GB, €564 (new (lowest in-stock DE board))

Mix-13G (smallest file), slow, partly in system RAM: Budget PC with RTX 3060 12GB, slow, partly in system RAM, €1,357 (estimate)

Prices moved: see Building a local LLM rig in the RAMageddon.

On a specific GPU

Rig Report waitlist

A written hardware plan for one model and budget. Planned price, not for sale yet.

What the Rig Report is