{"slug": "build-an-uncensored-abliterated-greek-native-llm-for-local-use-best-candidate-8b", "title": "Build an uncensored/abliterated Greek-native LLM for local use. Best candidate: ilsp/Llama-Krikri-8B-Instruct (Llama 3.1 8B Greek fine-tune).", "summary": "A user on a GMKtec EVO-X3 with an AMD Ryzen AI MAX+ 395 (Strix Halo) and 117.55 GiB unified memory is seeking guidance on building an uncensored, abliterated Greek-native LLM, naming ilsp/Llama-Krikri-8B-Instruct (a Llama 3.1 8B Greek fine-tune) as the best candidate. The plan is to abliterate the model with Heretic (heretic-llm), convert it to GGUF Q4_K_M, and run it on Vulkan via llama.cpp, with the user asking whether Heretic supports Llama-Krikri-8B, whether to abliterate safetensors before GGUF conversion or use abliterate.cpp on GGUF, and which quantization (Q4_K_M, Q5_K_M, or Q6_K) best balances Greek quality and speed. The user also asks for recommended llama.cpp Vulkan flags for Strix Halo (-ngl 99, -c 32768, flash attention, q8_0 KV cache, speculative decoding) and for any existing uncensored Greek models such as Krikri, Meltemi, or Sophea.", "body_md": "Hey everyone,\n\nSetup: GMKtec EVO-X3, AMD Ryzen AI MAX+ 395 (Strix Halo), Radeon 8060S, 117.55 GiB  unified memory, Ubuntu 24.04, Vulkan/RADV, llama.cpp built with GGML_VULKAN=ON. Running Qwen3-32B-heretic-Q8_0 on llama-server (127.0.0.1:8081).\n\nGoal: build an uncensored/abliterated Greek-native LLM for local use. Best candidate: ilsp/Llama-Krikri-8B-Instruct (Llama 3.1 8B Greek fine-tune). Plan: abliterate with Heretic (heretic-llm), convert to GGUF Q4_K_M, run on Vulkan.\n\nQuestions:\n\n1. Has anyone abliterated Llama-Krikri-8B or any Greek fine-tune? Does Heretic support it?\n2. Best workflow: abliterate safetensors then convert to GGUF, or use abliterate.cpp on GGUF? Any pitfalls?\n3. Best quantization for Greek on Strix Halo: Q4_K_M, Q5_K_M, Q6_K? Need quality/speed balance.\n4. Recommended llama.cpp Vulkan flags for Strix Halo: -ngl 99, -c 32768, flash attention, q8_0 KV cache, speculative decoding? Any known issues?\n5. Any existing uncensored Greek models I missed (Krikri, Meltemi, Sophea, etc.)?\n\nThanks!", "url": "https://wpnews.pro/news/build-an-uncensored-abliterated-greek-native-llm-for-local-use-best-candidate-8b", "canonical_source": "https://discuss.huggingface.co/t/build-an-uncensored-abliterated-greek-native-llm-for-local-use-best-candidate-ilsp-llama-krikri-8b-instruct-llama-3-1-8b-greek-fine-tune-plan-abliterate-with-heretic-heretic-llm-convert-to-gguf-q4-k-m-run-on-vulkan/180677#post_1", "published_at": "2026-09-22 02:48:37+00:00", "updated_at": "2026-09-22 02:55:01.515219+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "ai-infrastructure", "mlops", "ai-ethics"], "entities": ["GMKtec EVO-X3", "AMD Ryzen AI MAX+ 395", "Radeon 8060S", "Ubuntu 24.04", "llama.cpp", "ilsp/Llama-Krikri-8B-Instruct", "Heretic", "Qwen3-32B-heretic-Q8_0"], "alternates": {"html": "https://wpnews.pro/news/build-an-uncensored-abliterated-greek-native-llm-for-local-use-best-candidate-8b", "markdown": "https://wpnews.pro/news/build-an-uncensored-abliterated-greek-native-llm-for-local-use-best-candidate-8b.md", "text": "https://wpnews.pro/news/build-an-uncensored-abliterated-greek-native-llm-for-local-use-best-candidate-8b.txt", "jsonld": "https://wpnews.pro/news/build-an-uncensored-abliterated-greek-native-llm-for-local-use-best-candidate-8b.jsonld"}}