DEV.co
Open-Source LLM · empero-ai

Qwythos-9B-Claude-Mythos-5-1M

Qwythos-9B is a 9.4B-parameter reasoning model fine-tuned on Qwen3.5-9B with 500M+ tokens of Claude-style reasoning traces. It offers a 1M-token context window (via YaRN scaling), native function calling for tool use, and claimed significant improvements over its base model (+34 MMLU, +30 gsm8k-strict). Marketed as 'uncensored' for sensitive technical domains (cybersecurity, biology, pharmacology). Apache-2.0 licensed, ungated, and available on HuggingFace.

Source: HuggingFace — huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M
9.4B
Parameters
apache-2.0
License (OSI-approved)
Unknown
Context (tokens)
152.5k
Downloads (30d)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
Developerempero-ai
Parameters9.4B
Context windowUnknown
Licenseapache-2.0 — OSI-approved
Modality / tasktext-generation
Gated on HuggingFaceNo
Downloads152.5k
Likes723
Last updated2026-06-28
Sourceempero-ai/Qwythos-9B-Claude-Mythos-5-1M

What Qwythos-9B-Claude-Mythos-5-1M is

A full-parameter fine-tune of Qwen/Qwen3.5-9B using supervised fine-tuning (SFT) on internal Claude Mythos/Fable reasoning traces. Ships with YaRN rope-scaling (factor=4.0) baked into config.json, extending native 262k context to 1.048M tokens. Supports OpenAI/Qwen3.5-style function calling without wrapper or tool-specific fine-tune. Evaluation includes lm-evaluation-harness benchmarks (MMLU, gsm8k, ARC, GPQA); tool-use validation on 7 test prompts spanning math, cybersecurity, clinical pharmacology, and biochemistry. No published training code, hyperparameters, or convergence details.

Quickstart

Run Qwythos-9B-Claude-Mythos-5-1M locally

Load the open weights with 🤗 Transformers and generate — the same model, self-hosted.

quickstart.pypython
from transformers import pipelinepipe = pipeline("text-generation", model="empero-ai/Qwythos-9B-Claude-Mythos-5-1M")out = pipe("Explain retrieval-augmented generation in one sentence.",           max_new_tokens=128)print(out[0]["generated_text"])

Swap in vLLM or Ollama for production-grade serving. DEV.co can stand up the inference stack.

Deployment

How you'd run it

A typical self-hosted path — open weights, an inference server, your application.

DEV.co builds each layer — from GPU infrastructure to the application.

Best use cases

Whole-codebase code analysis and refactoring

1M context window allows loading multi-hundred-thousand-line repositories without RAG chunking. Native function calling supports tool-assisted debugging and cross-file architectural reasoning.

Long-trajectory agentic reasoning with tool integration

Model demonstrated reliable tool selection and source-cited answer generation on 7/7 hard-fact prompts (math, cybersecurity, clinical pharmacology). Suited for research automation, API-driven analysis, and multi-turn problem-solving with verbose tool outputs.

Technical Q&A in sensitive/specialized domains

Explicitly designed to engage cybersecurity, red-teaming, biomedical, pharmacology, and chemistry queries without refusal patterns. For organizations requiring frank technical assessment in regulated/sensitive fields without alignment overheads.

Running & fine-tuning it

VRAM: Estimated 18–24 GB (bfloat16) for full model on single GPU. At 1M context, 256k–512k tokens fit on H100/H200 with tensor parallelism or KV-cache offload; full 1M requires multi-GPU or aggressive quantization (ESTIMATE — not validated by card). FP8/INT8 quantization likely reduces to 10–14 GB. Inference batch-1 at 262k native context: ~12–16 GB estimated.

Full-parameter SFT applied by developers; no explicit LoRA/QLoRA guidance provided. Card notes 'full-fine-tune' as applied method. LoRA fine-tuning feasible but untested by authors; QLoRA 4-bit quantization likely viable for modest compute environments. Rope-scaling config in config.json may require caution if extending further; no guidance on gradient checkpointing or mixed-precision tuning stability at 1M context.

When to avoid it — and what to weigh

  • Strict content-safety or alignment requirements — Model is intentionally 'uncensored' and designed to engage seriously with red-teaming, exploits, and sensitive medical/pharmaceutical content. Not suitable for applications requiring strict output filtering or safety-alignment guarantees.
  • Short-context, latency-critical inference — YaRN scaling trades small short-context quality degradation for long-context performance (acknowledged in card). Single-GPU inference at 1M context requires multi-GPU or KV-cache offload; sub-256k contexts incur memory/latency overhead vs. pure 262k native window.
  • Production deployment without risk tolerance — Model is hosted by a small org (Empero AI); no SLA, formal support, or guaranteed maintenance roadmap stated. Evals provided are limited (100-sample per-task harness) and benchmarks are cherry-picked by developers. No third-party independent validation.
  • Fact-critical applications without tool grounding — Closed-book reasoning shows mixed results (e.g., −5.0% on GPQA vs. base). Tool-use validation limited to 7 hand-selected prompts. Production pipelines require mandatory retrieval/tool integration to avoid hallucinations on factual queries.

License & commercial use

Apache License 2.0 (OSI-approved). Covers source weights, architecture, and config.json modifications (YaRN scaling). Base model (Qwen/Qwen3.5-9B) is also Apache-2.0. License is permissive and unambiguous.

Apache-2.0 is an OSI-approved permissive license and explicitly permits commercial use, redistribution, and derivative works without royalty or attribution requirement (though attribution is recommended). No gating, no restricted-use terms in card. Commercial deployment, proprietary fine-tuning, and resale are legally permitted. However, no commercial support, SLA, or indemnification offered by Empero AI; buyer assumes liability for model behavior, hallucinations, and uncensored output in production environments.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceActive
DocumentationStrong
License clarityClear
Deployment complexityModerate
DEV.co fitGood
Assessment confidenceHigh
Security considerations

Model is intentionally uncensored and designed to provide substantive answers on cybersecurity exploitation, red-teaming methodologies, and sensitive biomedical content without refusal. Production use in customer-facing or moderated environments requires robust input validation, output filtering, and clear user disclaimers. No formal security audit, adversarial robustness testing, or jailbreak-resistance evaluation published. Tool-use feature (web search, code execution) introduces dependency on external service availability and code-injection risk if tool execution is not sandboxed. Inference with user-supplied code (Python executor tool) requires trusted environment.

Alternatives to consider

Qwen/Qwen3.5-9B (base model)

Same architecture, aligned variant. Larger safety margin but ~30–34 points lower on reasoning benchmarks. Consider if uncensored behavior is a liability.

Meta Llama-3.1-8B or Llama-3.3-70B

Well-maintained, broader adoption, strong community support, and formal commercial backing. Llama-3.1-8B is comparable in parameter count; Llama-3.3-70B offers stronger reasoning. Trade-off: Llama models are aligned and have stricter refusal patterns; smaller native context (8k–128k).

Mistral Large or Mixtral 8x7B

Permissive licenses, strong reasoning performance, active maintenance. Mistral Large supports longer context natively. Mixtral offers conditional computation. Neither advertises 'uncensored' posture; stricter on sensitive content.

Software development agency

Ship Qwythos-9B-Claude-Mythos-5-1M with senior software developers

Qwythos is a strong fit for long-context reasoning, agentic tool use, and specialized technical domains (cybersecurity, biomedical). If your team requires uncensored substantive Q&A without alignment overhead, run a proof-of-concept with vLLM or SGLang. Validate hallucination rates and tool-selection reliability on your domain before production. Contact Empero AI for scalable deployment guidance.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

Related on DEV.co

Explore the category and the services that help you build with it.

Qwythos-9B-Claude-Mythos-5-1M FAQ

Can I use Qwythos in a commercial product without paying licensing fees?
Yes. Apache-2.0 permits commercial use, modification, and resale without royalties or attribution requirement. You own the weights and can redistribute or fine-tune. However, Empero AI provides no commercial support, SLA, or liability indemnification. You are responsible for model behavior, hallucinations, uncensored outputs, and compliance with your jurisdiction's content policies.
What GPU does Qwythos require?
Single H100/H200 can serve ~256k–512k context tokens comfortably. For the full 1M window or higher throughput, use tensor parallelism (2–4 GPUs) or aggressive KV-cache offloading. For inference on consumer GPUs (RTX 4090, A100), quantization to INT8/FP8 (~10–14 GB) is recommended. Exact VRAM depends on batch size, sequence length, and precision (not validated by developers).
Does Qwythos support function calling out of the box?
Yes. Native support for OpenAI/Qwen3.5-style `<tool_call>` blocks. Pass `tools=[...]` to `apply_chat_template` and parse the model's `<tool_call>` output. No wrapper or separate tool-specific fine-tune required. Card provides tool-use validation on 7 hand-selected prompts (7/7 success), but broader robustness is Unknown.
Will Qwythos refuse harmful requests?
No. Model is explicitly uncensored and designed to engage substantively with red-teaming, cybersecurity exploitation, and sensitive biomedical/pharmaceutical content. If your use case requires strict content refusal or alignment, choose an aligned variant (e.g., Qwen3.5-9B base or Llama-3.1).

Software development & web development with DEV.co

Need help beyond evaluating Qwythos-9B-Claude-Mythos-5-1M? DEV.co is a software development agency offering software development services and web development for teams of every size. Our software developers and web developers build custom software, web applications, APIs, and open-source llms integrations — and maintain them long-term.

Evaluate Qwythos for Your Use Case

Qwythos is a strong fit for long-context reasoning, agentic tool use, and specialized technical domains (cybersecurity, biomedical). If your team requires uncensored substantive Q&A without alignment overhead, run a proof-of-concept with vLLM or SGLang. Validate hallucination rates and tool-selection reliability on your domain before production. Contact Empero AI for scalable deployment guidance.