You can deploy this model and start earning money today!

SZLHOLDINGS/
SZL-Khipu-1.5B-GGUF

Name: SZL-Khipu-1.5B-GGUF
Availability: InStock

SZLHOLDINGS/SZL-Khipu-1.5B

Views

No views yet

SZL Holdings — governed, receipted, verifiable

_{Part of the SZL Holdings governed estate — claims are designed to carry checkable receipts. Verification proves integrity & origin, never accuracy or performance.}

SZL-Khipu-1.5B — GGUF

A compact 1.5B model for governed agent navigation — quantized for everywhere.

The cut

Leaders treat GGUF as the model. We print on the card: signed hash does not cover these files. CPU-honest, receipt-honest.

Edge navigation that still fails closed, with a card that refuses to launder a quant as a weight.

Silhouette → leave → SZL

Leader	Take, then tweak
Anthropic	No GGUF. We keep the honesty they apply to API vs weights.
NVIDIA	TensorRT-LLM is their derived path. GGUF is ours. Same idea, smaller church.
Unsloth	Unsloth's GGUF export, labeled derived.

Nobody else ships this combination. That is the point of a one-of-one.

Intended use

llama.cpp / Ollama / LM Studio. Still proposal-only.

Limitations

Derived. Numerics drift vs BF16.
Do not cite GGUF as the signed checkpoint.

Canonical GitHub: szl-holdings/szl-serve

GGUF quantizations of SZL-Khipu-1.5B — a QLoRA fine-tune of Qwen2.5-1.5B-Instruct for governed, grounded-only navigation of the SZL receipt lake. Small enough for a laptop, honest enough for an audit.

Published provenance: the base model ships with owner-signed training and eval receipts. They are Ed25519 signatures over canonical JSON and chain the evaluation receipt to the training receipt. This repo carries those receipts plus the repo-declared public key so you can verify repository-key continuity and receipt integrity before you load a tensor. They are not DSSE envelopes; the repository does not establish external key provenance, and an owner signature is not an independent evaluation.

Quants

File	Bits	Size	Uploaded-byte SHA-256 (Hub LFS OID)	Use when
SZL-Khipu-1.5B-Q4_K_M.gguf	4-bit	0.99 GB	`13c1a1993063e1dff92f7413ccf48eaca6d48efc8801ae9af35961ae3396623a`	Default - best size/quality balance
SZL-Khipu-1.5B-Q5_K_M.gguf	5-bit	1.13 GB	`3bf460ac163c5dc952c273999c38a41349e3e6d666e4b713aed22c996860fd4c`	More quality headroom
SZL-Khipu-1.5B-Q8_0.gguf	8-bit	1.65 GB	`6aff1087f64631679f4cdf032613aee6911dbde38cd3bac6b81bf63741a56f0d`	Near-lossless CPU inference
SZL-Khipu-1.5B-F16.gguf	16-bit	3.09 GB	`2348ee342efe639e100f3fb31a3dc11b8c12d8c43ecfe45e18041b9f94c71a12`	Reference / requantizing

Chat template (Qwen2.5 ChatML) is embedded in every file.

Run it

Ollama

ollama run hf.co/SZLHOLDINGS/SZL-Khipu-1.5B-GGUF:Q4_K_M

llama.cpp

llama-cli -hf SZLHOLDINGS/SZL-Khipu-1.5B-GGUF:Q4_K_M -p "Navigate: which receipt signed decision d-42?"

LM Studio — search SZLHOLDINGS/SZL-Khipu-1.5B-GGUF, pick Q4_K_M.

Prompt contract

The user turn is a single JSON object {query, candidates:[{nodeId, nodeKind, label, note}]} — handles only, never node content — and the model returns a single JSON plan (decision=NAVIGATE citing offered handles, or decision=ABSTAIN with an abstainReason) per khipu.schema.json. The full contract and expected output shape live on the BrainNavigator card.

Verify before you trust

bash

# The owner-signed receipts travel with the weights:
#   training_receipt.signed.json; eval_receipt.signed.json; owner_pubkey.json
# They are Ed25519 signatures over canonical JSON, not DSSE envelopes.
# Verify them offline against the repo-declared public key before use.

Quantization: llama.cpp convert_hf_to_gguf.py -> llama-quantize (F16 -> Q4_K_M / Q5_K_M / Q8_0), 2026-07-15. Quantization changes numerics; the signed evaluation receipt covers the pre-quantized BrainNavigator evaluation artifact described by that receipt, not any GGUF. The LFS hashes above bind the exact uploaded GGUF bytes. No post-quantization quality evaluation or independent benchmark is claimed.

Governed AI you can prove.

🛡️ a-11-oy.com · base model + full card → · source/harness · org page

_{Lambda = Conjecture 1, never green; owner-signed receipts verified against a repo-declared key; no independent benchmark or post-quant evaluation claimed}

🛡️ SZLHOLDINGS on Hugging Face → · a-11-oy.com → · Estate hub — live →

Governed AI you can prove.

_{SLSA: L1 honest · L2 attested · L3 roadmap. Λ = Conjecture 1 (advisory, never a theorem). Trust ceiling 0.97 — never 100%. Labels honest by default: MEASURED / REPORTED / MODELED / HEURISTIC / UNKNOWN / UNAVAILABLE. locked-proven = exactly 8 {F1,F4,F7,F11,F12,F18,F19,F22}.}