license: apache-2.0
language:

• en
  base_model: FrostWolfAI/Frost-Cyber-Mini-Uncensored-v1.1
  base_model_relation: quantized
  pipeline_tag: text-generation
  library_name: gguf
  tags:
• gguf
• llama.cpp
• cybersecurity
• uncensored
• abliterated
• spark2_5
• agentic
• tool-use

Frost Cyber Mini Uncensored v1.1 — GGUF

By Vatsal Bajpai (@xblack) · FrostWolfAI Labs — GGUF quants of Frost-Cyber-Mini-Uncensored-v1.1, a compact, fast, local cybersecurity and software-engineering assistant with an agentic tool-use phase, for red-team, OSINT, CTI, secure coding and agentic workflows.

Benchmarked — see Benchmarks below, or the base model card for full details.

Quants

4B params (Spark2_5ForCausalLM, 36 layers). Pick by your VRAM/quality trade-off — IQ4_XS / Q4_K_M are the usual local sweet spots; Q8_0 is near-lossless; BF16 is the full-precision reference.

Benchmarks

Evaluated in thinking mode, temperature 0.0, greedy single-sample, Q8_0 GGUF at 232k context. Full details in the base model card.

⚠️ Always run with thinking enabled — with thinking off, this model degrades severely (it echoes JSON instead of answering). Agentic benchmarks (Terminal-Bench, DeepSWE, AutomationBench) are queued and will be added as they land.

Run with llama.cpp (Windows)

The custom spark2_5 architecture is supported by llama.cpp. The chat template must be supplied explicitly with --chat-template-file — download chat_template.jinja from the base repo.

REM Q8_0, full 232k context, 2 unified-KV slots.
llama-server.exe ^
  -m Frost-Cyber-Mini-Uncensored-v1.1-Q8_0.gguf ^
  -ngl 99 ^
  -np 2 -kvu -c 232000 ^
  --host 127.0.0.1 --port 8080 ^
  -fa on -ctk q8_0 -ctv q8_0 ^
  -b 4096 -ub 2048 ^
  --jinja --chat-template-file chat_template.jinja ^
  --reasoning-budget 8192

Do not add DRY or other repetition-penalty samplers for agentic coding. They penalize repeated token sequences, but coding requires reproducing file paths, identifiers and edit targets byte-for-byte — a repetition penalty mutates those verbatim strings and corrupts tool calls. If a small model loops, break it at the client level (de-duplicate identical tool calls, cap steps) and/or use a small temperature (~0.3–0.4).

Reasoning / thinking control

Per request via reasoning_effort: off disables thinking; low (default) / high enable it (near-identical on a 4B — treat as on/off). The hard thinking-token ceiling is the server's --reasoning-budget, not the template.

Known limitation

Do not rely on this model for CVE details looked up by ID — it can invent a plausible-but-wrong bug (inherited from the base model's parametric knowledge). Verify CVE facts against a primary source, or give the model a lookup tool.

Intended use

For authorized security testing, research, defense and education. Refusals are removed, so you are responsible for how you use it and for following applicable law.

_{Everything here is released openly. If it's useful to you and you'd like to support more open-source work on AI, a coffee goes a long way — entirely optional.}