nassila-sanad-e4b

Nassila Sanad E4B — RETIRED (legacy)

Checkpoint: S12 (legacy train label v1.12)

Status (2026-08): E4B S12 retired as the default tier — replaced by nassila-sanad-4b (S15, Qwen 3.5 4B). Card kept for legacy users of the published E4B GGUF; no new trains.

Local GGUF for Sanad in Nassila — checks manuscript claims against source excerpts and returns structured JSON with verdicts and verbatim quotes.

File: nassila-sanad-e4b-q6_k.gguf · Q6_K · ~5.8 GB
Default tier (now): nassila-sanad-4b · Quality tier: nassila-sanad-12b

Part of Nassila Ouroboros — seven workers with deterministic checks plus optional local models.

Sanad today: validated on abstract excerpts (Tier 2). Full paper body text is planned (Tier 3).

Default-tier validation: PASS

Usage

Quick start (Nassila + LM Studio)

Recommended — download this GGUF, load it in LM Studio, and start the Local Server at http://localhost:1234.

In Nassila: Settings → Passage grounding → runner LM Studio → model nassila-sanad-e4b (or the id LM Studio shows).

Ollama

Requires Ollama 0.5+ and a public Hugging Face repo.

Pull from Hub:

ollama pull huggingface.co/QinEmPeRoR93/nassila-sanad-e4b:Q6_K

In Nassila: runner Ollama → base URL http://localhost:11434 → model name from ollama list (often nassila-sanad-e4b:Q6_K).

<details> <summary>Modelfile fallback (private repo or pull tag not indexed)</summary>

FROM https://huggingface.co/QinEmPeRoR93/nassila-sanad-e4b/resolve/main/nassila-sanad-e4b-q6_k.gguf
PARAMETER num_ctx 4096

ollama create nassila-sanad-e4b -f Modelfile

</details>

Advanced (llama.cpp / vLLM)

Serve the GGUF with any OpenAI-compatible server (ctx-size 4096; requires a recent llama.cpp build with gemma4_unified support). Point Nassila at your base URL and exposed model id.

llama-server -m nassila-sanad-e4b-q6_k.gguf \
  --host 127.0.0.1 --port 1234 --ctx-size 4096 --n-gpu-layers 99

Limitations

• Trained on abstract excerpts (Tier 2); full paper body (Tier 3) planned.
• Advisory only — use with Nassila deterministic guardrails.
• Not bundled in the Nassila installer.

Base model

google/gemma-4-E4B-it · Gemma Terms of Use