| ---
|
| license: other
|
| license_name: qwen
|
| license_link: https://huggingface.co/Qwen
|
| base_model:
|
| - Qwen/Qwen3.5
|
| tags:
|
| - agent
|
| - tool-calling
|
| - function-calling
|
| - gguf
|
| - ollama
|
| - long-context
|
| pipeline_tag: text-generation
|
| library_name: transformers
|
| ---
|
|
|
| # Engrym Seed Flash 4B
|
|
|
| Part of **Engrym Seed** — Orvyth's seed-tier local model family for **tool-using agents**. Qwen3.5
|
| hybrid linear-attention architecture, **262,144-token native context**, first-class tool calling.
|
|
|
| The best agent build — fastest to act, and the value pick of the ladder.
|
|
|
| **Weights are distributed via the Ollama registry.**
|
|
|
| ```bash
|
| ollama run Orvyth/engrym-seed:flash
|
| ```
|
|
|
| | | |
|
| |---|---|
|
| | Size | 4.6 GB |
|
| | 77-task score | **124/143** (86.7%) |
|
| | Tool calling | **12/12** verified |
|
| | Context | 262,144 native (default `num_ctx` 32,768) |
|
| | Quantization | Q8_0 |
|
|
|
| ## The full ladder
|
|
|
| | Tag | Class | Size | 77-task |
|
| |---|---|---:|---:|
|
| | `:nano` | Nano 2B | 2.1 GB | 90.8/143 |
|
| | `:flash` | Flash 4B | 4.6 GB | 124/143 |
|
| | `:base` | Base 9B | 9.5 GB | 131/143 |
|
| | `:pro-27b-q4` | Pro 27B v2 Q4 | 16.5 GB | 134/143 |
|
| | `:pro` | Pro 27B v2 Q8 | 28.6 GB | 137/143 |
|
| | `:pro-e` | Pro-E 27B *(experimental)* | 28.6 GB | 137/143 |
|
|
|
| ## Evaluation
|
|
|
| 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.
|
|
|
| **First-party** numbers. Repeated runs on an uncontended GPU are deterministic (zero spread across
|
| n=2 for every model measured). Public reproduction receipts are pending.
|
|
|
| ## Compute modes — the score is a floor
|
|
|
| Asking the model to work *deliberately* recovers points on tasks it otherwise fails, and the gain is
|
| largest for the smallest models (Nano +11.8, Flash +6, Base +3, Pro-E +0). On the small end that is
|
| worth more than a model upgrade.
|
|
|
| ## Defaults
|
|
|
| `temperature 0.2` · `top_p 0.9` · `top_k 20` · `num_ctx 32768` · `num_predict 8192`
|
|
|
| If a prompt exceeds `num_ctx`, Ollama returns HTTP 400 — it does not silently truncate.
|
|
|
| ## Lineage
|
|
|
| `Qwen/Qwen3.5` base → Ornith-1.0-9B x Qwythos-9B TIES merge (9B line) → Orvyth identity and
|
| chip-calling LoRA merged into the weights → converted and quantized in-house.
|
|
|
| ## Limits
|
|
|
| - First-party scores; treat small gaps between adjacent models as unresolved.
|
| - The identity tune is light; a heavy external system prompt can pull behavior toward the base model.
|
| - The 27B is much slower per tool call than the 9B and smaller.
|
| - No MTP speculative-decoding head in these builds.
|
| - Tags are mutable — pin the digest for production and evaluations.
|
|
|
| ---
|
|
|
| **ORVYTH** - Intelligence. Governed. *Ground truth over hype. Prove before you claim.*
|
|
|
