Sophea-Titan-1-GGUF

Sophea-Titan-1-GGUF

GGUF (llama.cpp) builds of the text language model of KIEFERSA/Sophea-Titan-1 (Qwen3.6-27B, hybrid GatedDeltaNet + full attention). Vision is not carried into GGUF. Non-thinking, greedy. Requires a llama.cpp build with qwen35 support.

Files

• Sophea-Titan-1.Q4_K_M.gguf — 16.5 GB
• Sophea-Titan-1.Q5_K_M.gguf — 19.2 GB
• Sophea-Titan-1.Q8_0.gguf — 28.6 GB

Runtime compatibility

These are the text language model only (no vision). The architecture is Qwen3.6/Qwen3.5's hybrid GatedDeltaNet + full attention, so the runtime's bundled llama.cpp must be recent enough to support the qwen35 architecture. If a runtime errors with "unknown model architecture: qwen35", it simply needs a newer llama.cpp.

<div style="overflow-x:auto"> <table style="width:100%;border-collapse:collapse;font-size:13px;font-variant-numeric:tabular-nums;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif"> <thead><tr> <th style="padding:10px 8px;text-align:left;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;">Runtime</th> <th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;">Status</th> </tr></thead><tbody> <tr> <td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);"><strong>llama.cpp</strong> (recent build)</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">✅ <strong>Verified</strong> — loads and runs</td> </tr> <tr> <td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);font-weight:700;">LM Studio</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">✅ Works when its runtime is a <code style="font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:.9em;background:rgba(10,128,67,.10);padding:1px 5px;border-radius:5px">qwen35</code>-capable <code style="font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:.9em;background:rgba(10,128,67,.10);padding:1px 5px;border-radius:5px">llama.cpp</code> — use the latest LM Studio and select the newest runtime</td> </tr> <tr> <td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);"><strong>Ollama</strong> (≥ 0.32)</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">✅ Works — import the GGUF; serve chat with <code style="font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:.9em;background:rgba(10,128,67,.10);padding:1px 5px;border-radius:5px">think: false</code> (non-thinking model)</td> </tr> </tbody></table></div>

System requirements (local / CPU)

Runs on a normal machine — no GPU required. You need roughly the file size in RAM, plus a couple GB.

<div style="overflow-x:auto"> <table style="width:100%;border-collapse:collapse;font-size:13px;font-variant-numeric:tabular-nums;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif"> <thead><tr> <th style="padding:10px 8px;text-align:left;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;">Quant</th> <th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;">Size</th> <th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;">Min RAM</th> <th style="padding:10px 8px;text-align:center;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;">Comfortable</th> </tr></thead><tbody> <tr> <td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);">Q4_K_M</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">16.5 GB</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">24 GB</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">32 GB</td> </tr> <tr> <td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);">Q5_K_M</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">19.2 GB</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">24 GB</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">32 GB</td> </tr> <tr> <td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);">Q8_0</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">28.6 GB</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">32 GB</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">48 GB</td> </tr> </tbody></table></div>

CPU: any modern x86-64 (AVX2) or Apple Silicon; 8+ cores for usable speed. A GPU is optional (faster), not required.

Usage

Download a quant (private repo — use your HF token):

huggingface-cli download KIEFERSA/Sophea-Titan-1-GGUF Sophea-Titan-1.Q4_K_M.gguf \
  --local-dir ./sophea --token $HF_TOKEN

llama.cpp (verified) — non-thinking, greedy:

llama-cli -m ./sophea/Sophea-Titan-1.Q4_K_M.gguf \
  -p "Ποια είναι η πρωτεύουσα της Ελλάδας;" -n 64 --temp 0

LM Studio — place under publisher/model/, then pick it in the model loader:

mkdir -p ~/.lmstudio/models/KIEFERSA/Sophea-Titan-1-GGUF
cp ./sophea/Sophea-Titan-1.Q4_K_M.gguf ~/.lmstudio/models/KIEFERSA/Sophea-Titan-1-GGUF/

Ollama (≥ 0.32 — older versions error with "unknown architecture: qwen35"):

printf 'FROM ./sophea/Sophea-Titan-1.Q4_K_M.gguf\nPARAMETER temperature 0\n' > Modelfile
ollama create sophea-titan-1 -f Modelfile
ollama run sophea-titan-1 --think=false "Ποια είναι η πρωτεύουσα της Ελλάδας;"

Non-thinking model: pass think: false (CLI --think=false, or "think": false in the API) — otherwise the chat reply comes back empty. Ollama also serves an OpenAI-compatible API at http://localhost:11434/v1.

Serve an OpenAI-compatible API with llama.cpp's llama-server:

llama-server -m ./sophea/Sophea-Titan-1.Q4_K_M.gguf \
  --host 0.0.0.0 --port 8080 --api-key sk-local -c 8192

Call it with the OpenAI SDK — just point base_url at the server:

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8080/v1", api_key="sk-local")
resp = client.chat.completions.create(
    model="sophea-titan-1",            # any name — the loaded GGUF is served
    messages=[{"role": "user", "content": "Ποια είναι η πρωτεύουσα της Ελλάδας;"}],
    temperature=0,
)
print(resp.choices[0].message.content)

Or with plain curl:

curl http://localhost:8080/v1/chat/completions \
  -H "Authorization: Bearer sk-local" -H "Content-Type: application/json" \
  -d '{"model":"sophea-titan-1","messages":[{"role":"user","content":"Γεια σου"}],"temperature":0}'

Quants: Q4_K_M (16.5 GB, recommended) · Q5_K_M (19.2 GB) · Q8_0 (28.6 GB, near-lossless).

License

Inherits the Qwen3.6-27B base-model license.