Downloads · 30 days
5
3% of all-time downloads
cipher-sft-merged-Q4_K_M-GGUF
Auroraventures/cipher-sft-merged-Q4_K_M-GGUF
cipher-sft-merged-Q4_K_M-GGUF is a text generation model from Auroraventures. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as cc-by-nc-4.0.
A 4-bit K-quantized GGUF of Auroraventures/cipher-sft-merged for llama.cpp / Ollama / LM Studio on consumer GPUs (≈ 18 GB).
All-time downloads
167
Public
Repo size
18.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf18.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- llama.cpp
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Apr 14, 2026
- Updated
- Apr 18, 2026
- SHA
- cd5d3e9c
Try a prompt
Base models
Model card
From the Hugging Face model README
Cipher SFT v1 — Q4_K_M GGUF 🦑
A 4-bit K-quantized GGUF of Auroraventures/cipher-sft-merged for llama.cpp / Ollama / LM Studio on consumer GPUs (≈ 18 GB).
Ollama
cat > Modelfile <<'EOF'
FROM ./cipher-sft-merged-Q4_K_M.gguf
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER repeat_penalty 1.05
SYSTEM "You are Cipher, the Code Kraken. Emit complete single-file HTML."
EOF
ollama create kin-cipher -f Modelfile
ollama run kin-cipher "Build a portfolio hero with Lenis + GSAP"
llama.cpp
./llama-server -m cipher-sft-merged-Q4_K_M.gguf --chat-template gemma --ctx-size 8192
Gotcha: For SFT checkpoints, use
raw:truein the Ollama/api/generaterequest and apply the Gemma-4 chat template manually — Ollama's auto-template can misfire on merged weights.
License
CC-BY-NC-4.0. Gemma-4 base terms apply.
Built with 🦑 by Aurora Ventures.
- Task
- Text Generation
- Library
- llama.cpp
- License
- cc-by-nc-4.0
- Languages
- en
- Created
- Apr 14, 2026
- Updated
- Apr 18, 2026