Downloads · 30 days
0
Orvyth/engrym-seed-base-9b
engrym-seed-base-9b is a text generation model from Orvyth. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Orvyth's seed-tier brain — the recommended member of a local model family built for tool-using agents. Qwen3.5 hybrid linear-attention architecture, 262,144-token native context, first-class tool calling.
Downloads · 30 days
0
Access
Public
Updated Aug 15, 2026
Repo size
—
Likes
0
Public
Click a slice to open those files.
.md3.4 KB · 69%
From the Hugging Face model README
Orvyth's seed-tier brain — the recommended member of a local model family built for tool-using agents. Qwen3.5 hybrid linear-attention architecture, 262,144-token native context, first-class tool calling.
Weights are distributed via the Ollama registry.
ollama run Orvyth/engrym-seed:base
| Tag | Class | Size | 77-task | Tool calls |
|---|---|---|---|---|
:nano | Nano 2B | 2.1 GB | 90.8/143 | 12/12 |
:flash | Flash 4B | 4.6 GB | 124/143 | 12/12 |
:base | Base 9B | 9.5 GB | 131/143 | 12/12 |
:pro-27b-q4 | Pro 27B v2 Q4 | 16.5 GB | 134/143 | 12/12 |
:pro | Pro 27B v2 Q8 | 28.6 GB | 134/143 | 12/12 |
:pro-e | Pro-E 27B (experimental) | 28.6 GB | 137/143 | 12/12 |
77 tasks · 143 points · temperature=0 · max_tokens=16384 · seed=42 · one attempt · deterministic
validators · no LLM judge. Scores are bound to the exact published blobs.
These are first-party numbers. Repeated runs on an uncontended GPU are deterministic (zero spread across n=2 for every model measured), Receipts: https://huggingface.co/datasets/Orvyth/engrym-seed-receipts
Asking the model to work deliberately (reason step by step, verify against every constraint, then answer) recovers points on tasks it otherwise fails. Base: 131 → 134. The gain is largest for the smallest models — Nano gains +11.8. On the small end, that is worth more than a model upgrade.
temperature 0.2 · top_p 0.9 · top_k 20 · num_ctx 32768 · num_predict 8192
Native context is 262,144; larger requests are clamped. Default is 32,768 because defaulting to the
native maximum made a 9.5 GB model request ~19 GB of RAM to start. If a prompt exceeds num_ctx,
Ollama returns HTTP 400 — it does not silently truncate.
| Stage | Provenance |
|---|---|
| Base | Qwen/Qwen3.5 — hybrid linear-attention |
| Merge | Ornith-1.0-9B × Qwythos-9B — TIES, 0.5 / 0.5 |
| Tune | Orvyth identity + chip-calling; LoRA merged into the weights |
| Build | Converted and quantized in-house with Orvyth trainkit |
Weights, identity, and tool-call generation. Memory, governed tool execution, safety enforcement, adapters and multi-agent routing are Orvyth platform concerns, not part of the GGUF. Tool calling is an output capability — the host validates, authorizes and executes.
ORVYTH — Intelligence. Governed. Ground truth over hype. Prove before you claim.