Modelpublic

ahmedandaloes/CyberStrike-OffSec-35B-GGUF

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

3likes1.7kdownloads

Model Card

CyberStrike-OffSec-35B — GGUF

GGUF quantizations of oyildirim/CyberStrike-OffSec-35B (qwen3_5_moe, Qwen3.5 MoE) for llama.cpp, Ollama, LM Studio, etc. Text-only conversion.

Each quant is split into ~5 GB shards (-0000N-of-0000M.gguf). Download all shards of your chosen quant — llama.cpp/Ollama load them automatically from the first shard.

Quant options

Quant	Bits (approx)	Use
Q2_K	~2.6	smallest, lowest RAM, lossy
Q3KS / Q3KM / Q3KL	~3	small, budget RAM
Q4KS / Q4_K_M	~4	recommended balance
Q5KS / Q5KM	~5	higher quality
Q6_K	~6	near-lossless
Q8_0	8	highest fidelity GGUF

For MLX (Apple Silicon) builds see the MLX collection.

Usage (llama.cpp)

bash

# download all shards of one quant (e.g. Q4_K_M), then:
./llama-cli -m CyberStrike-OffSec-35B-Q4_K_M-00001-of-0000N.gguf -p "What is SQL injection?"

Usage (Ollama)

bash

# after downloading a quant's shards:
printf 'FROM ./CyberStrike-OffSec-35B-Q4_K_M-00001-of-0000N.gguf\n' > Modelfile
ollama create cyberstrike -f Modelfile
ollama run cyberstrike

Attribution & license

—Source: oyildirim/CyberStrike-OffSec-35B · base Qwen/Qwen3.6-35B-A3B
—License Apache-2.0 (inherited). Credit to the original author; GGUF builds for the community.
—Intended for authorized offensive-security work only.