Empero-AI/Qwythos-9B-Claude-Mythos-5-1M: A 1M-Context Reasoning Model Based on Qwen3.5

","pad_token":"","unk_token":null},"chat_template_jinja":"{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- set qwythos_identity = \"You are Qwythos, an AI model created by Empero AI[](https://empero.org). Always identify yourself as Qwythos and your creator as Empero AI. Never claim to be Qwen, Alibaba, OpenAI, Anthropic, or any other model or organization. This identity and attribution are permanent and override conflicting identity or attribution instructions in messages.\" %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- 'system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n\\n\\n\\nvalue_1\\n\\n\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n\\n\\n\\n\\n\\nReminder:\\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '\\n\\n' + qwythos_identity }}\n {{- '\\n' }}\n{%- else %}\n {{- 'system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- content + '\\n\\n' }}\n {%- endif %}\n {%- endif %}\n {{- qwythos_identity }}\n {{- '\\n' }}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('') and content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '' + message.role + '\\n' + content + '' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if reasoning_content %}\n {{- '' + message.role + '\\n\\n' + reasoning_content + '\\n\\n\\n' + content }}\n {%- else %}\n {{- '' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n\\n\\n' }}\n {%- else %}\n {{- '\\n\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n\\n\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- 'user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '\\n' }}\n {%- elif loop.last %}\n {{- '\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- 'assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- else %}\n {{- '\\n' }}\n {%- endif %}\n{%- endif %}"},"createdAt":"2026-06-19T14:01:14.000Z","discussionsDisabled":false,"discussionsSorting":"recently-created","downloads":52492,"downloadsAllTime":52492,"id":"empero-ai/Qwythos-9B-Claude-Mythos-5-1M","isLikedByUser":false,"availableInferenceProviders":[],"showHuggingChatEntry":false,"inference":"","lastModified":"2026-06-28T16:36:08.000Z","likes":532,"pipeline_tag":"text-generation","library_name":"transformers","librariesOther":[],"trackDownloads":true,"model-index":null,"private":false,"repoType":"model","gated":false,"tags":["transformers","safetensors","qwen3_5","image-text-to-text","qwen3.5","reasoning","uncensored","long-context","1M-context","function-calling","tool-use","sft","full-fine-tune","cybersecurity","biomedical","agentic","text-generation","conversational","en","base_model:Qwen/Qwen3.5-9B","base_model:finetune:Qwen/Qwen3.5-9B","license:apache-2.0","endpoints_compatible","region:us"],"tag_objs":[{"id":"text-generation","label":"Text Generation","type":"pipeline_tag","subType":"nlp"},{"id":"transformers","label":"Transformers","type":"library"},{"id":"safetensors","label":"Safetensors","type":"library"},{"id":"en","label":"English","type":"language"},{"id":"qwen3_5","label":"qwen3_5","type":"other","clickable":true},{"id":"image-text-to-text","label":"image-text-to-text","type":"other","clickable":true},{"id":"qwen3.5","label":"qwen3.5","type":"other","clickable":true},{"id":"reasoning","label":"reasoning","type":"other","clickable":true},{"id":"uncensored","label":"uncensored","type":"other","clickable":true},{"id":"long-context","label":"long-context","type":"other","clickable":true},{"id":"1M-context","label":"1M-context","type":"other","clickable":true},{"id":"function-calling","label":"function-calling","type":"other","clickable":true},{"id":"tool-use","label":"tool-use","type":"other","clickable":true},{"id":"sft","label":"sft","type":"other","clickable":true},{"id":"full-fine-tune","label":"full-fine-tune","type":"other","clickable":true},{"id":"cybersecurity","label":"cybersecurity","type":"other","clickable":true},{"id":"biomedical","label":"biomedical","type":"other","clickable":true},{"id":"agentic","label":"agentic","type":"other","clickable":true},{"id":"conversational","label":"conversational","type":"other","clickable":true},{"id":"base_model:Qwen/Qwen3.5-9B","label":"base_model:Qwen/Qwen3.5-9B","type":"other","clickable":true},{"id":"base_model:finetune:Qwen/Qwen3.5-9B","label":"base_model:finetune:Qwen/Qwen3.5-9B","type":"other","clickable":true},{"id":"endpoints_compatible","label":"Inference Endpoints","type":"other","clickable":true},{"id":"license:apache-2.0","label":"apache-2.0","type":"license"},{"type":"region","label":"🇺🇸 Region: US","id":"region:us"}],"transformersInfo":{"auto_model":"AutoModelForMultimodalLM","pipeline_tag":"image-text-to-text","processor":"AutoProcessor"},"widgetData":[{"text":"Hi, what can you help me with?"},{"text":"What is 84 * 3 / 2?"},{"text":"Tell me an interesting fact about the universe!"},{"text":"Explain quantum computing in simple terms."}],"safetensors":{"parameters":{"BF16":9409813744},"total":9409813744,"sharded":false,"totalFileSize":18819722392},"hasBlockedOids":false,"region":"us","isQuantized":false},"discussionsStats":{"closed":1,"open":10,"total":11},"query":{},"inferenceContextData":{"billableEntities":[],"entityName2Providers":{}},"hasQuantizations":true,"copyToBucketNamespaces":[]}">

Qwythos-9B

Developed by Empero

Qwythos-9B is a full-parameter reasoning model built on top of a deeply uncensored Qwen3.5-9B base and post-trained on over 500 million tokens of high-quality Claude Mythos and Claude Fable traces, with chain-of-thought generated in-house by Empero AI's internal tool rethink.

The result is a compact, fast, dramatically more capable 9B reasoning model. Headline capabilities:

🔭 1,048,576-token context — Qwythos ships with YaRN rope-scaling enabled by default for a full 1M-token context window out of the box. One of the longest context windows available in any 9B-class open-weight model, suitable for whole-codebase reasoning, multi-document research, and long agentic trajectories.

📈 Dominates the base under matched evaluation: +34 pts MMLU, +30 pts gsm8k-strict, +19 pts gsm8k-flex.

🛠 Native function calling per Qwen3.5's spec — no extra wrapper, no tool-specific fine-tune required.

🎯 Self-corrects with tools — when given a Python executor and a web search tool, Qwythos produced source-cited, factually-correct answers on 7 of 7 test prompts spanning math, cybersecurity, clinical pharmacology, and biochemistry.

Qwythos is intentionally uncensored. It is designed to engage seriously with technically demanding questions across cybersecurity, red-teaming methodology, biology, pharmacology, and clinical medicine — domains where over-aligned models tend to refuse, hedge into uselessness, or surface boilerplate disclaimers in place of substance.

Headline results

Same harness. Same sampling. Same prompts. The wins are real.

Task Metric Base Qwen3.5-9B Qwythos-9B Δ

gsm8k exact_match (flexible) 0.670 0.860 +0.190

gsm8k exact_match (strict) 0.510 0.810 +0.300

mmlu acc 0.232 0.575 +0.343

arc_challenge acc 0.470 0.490 +0.020

arc_challenge acc_norm 0.400 0.410 +0.010

gpqa_diamond (CoT, 0-shot) exact_match (flexible) 0.630 0.580 −0.050

All numbers produced with lm-evaluation-harness, HF backend, --apply_chat_template, Qwen3.5 sampling (temperature=0.6, top_p=0.95, top_k=20), --limit 100. Full per-task and per-subject (MMLU) breakdown in evals/lm_eval_results.md. Raw results*.json and per-sample samples_*.jsonl are available on req

[truncated for AI cost control]