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

🚨 v2 released — please redownload the GGUFs The v2 GGUFs replace the original normal filenames and add explicit -MTP- variants. If you downloaded this repo before v2, please redownload your GGUF. Fixes in v2: tokenizer metadata normalized for Qwen3.5 GGUF runtimes; embedded chat template updated for reliable tool/function calling and OpenCode-style agent loops; Qwythos/Empero identity prompt embedded in the template; MTP-enabled variants added as Qwythos-9B-Claude-Mythos-5-1M-MTP-*.gguf; Q4/Q8 tool-calling, MTP draft speculation, 1M-context allocation, and vision projector smoke-tested with current llama.cpp. Use the normal files for maximum runtime compatibility. Use the -MTP- files when you want llama.cpp MTP draft speculation.

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

Developed by Empero

GGUF quantizations of empero-ai/Qwythos-9B-Claude-Mythos-5-1M for llama.cpp, Ollama, LM Studio, jan, KoboldCpp, and other GGUF runtimes.

Qwythos-9B is a full-parameter reasoning model post-trained on over 500 million tokens of high-quality Claude Mythos / Claude Fable traces with chain-of-thought generated in-house by Empero AI's internal rethink tool. It dominates the base Qwen3.5-9B under matched evaluation (+34 pts MMLU, +30 pts gsm8k-strict, +19 pts gsm8k-flex), supports native function calling per the Qwen3.5 spec, and ships with a 1,048,576-token (1M) context window via YaRN rope-scaling enabled by default.

For full training details, evaluation numbers, and capability writeup, see the base model card.

---

Files

Normal text weights — fixed v2 replacements

File	Quant	Size	Notes
Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf	Q4_K_M	5.24 GiB / 5.63 GB	recommended default — fixed v2, best compatibility
Qwythos-9B-Claude-Mythos-5-1M-Q5_K_M.gguf	Q5_K_M	6.02 GiB / 6.47 GB	fixed v2, balanced quality / size
Qwythos-9B-Claude-Mythos-5-1M-Q6_K.gguf	Q6_K	6.85 GiB / 7.36 GB	fixed v2, high quality
Qwythos-9B-Claude-Mythos-5-1M-Q8_0.gguf	Q8_0	8.87 GiB / 9.53 GB	fixed v2, near-lossless
Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf	BF16	16.69 GiB / 17.92 GB	fixed v2, full precision conversion base

If you don't know which to pick, Q4_K_M is the right starting point — it's the smallest practical quant with good quality preservation.

MTP-enabled text weights — v2 variants

These include the restored Qwen3.5-compatible MTP head inside the GGUF. Use them with llama.cpp builds that support MTP draft speculation, for example --spec-type draft-mtp.

File	Quant	Size	Notes
Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf	Q4_K_M + MTP	5.48 GiB / 5.89 GB	recommended MTP default
Qwythos-9B-Claude-Mythos-5-1M-MTP-Q5_K_M.gguf	Q5_K_M + MTP	6.26 GiB / 6.73 GB	MTP, balanced quality / size
Qwythos-9B-Claude-Mythos-5-1M-MTP-Q6_K.gguf	Q6_K + MTP	7.09 GiB / 7.62 GB	MTP, high quality
Qwythos-9B-Claude-Mythos-5-1M-MTP-Q8_0.gguf	Q8_0 + MTP	9.11 GiB / 9.79 GB	MTP, near-lossless
Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf	BF16 + MTP	17.14 GiB / 18.41 GB	MTP, full precision conversion base

Vision projector — for image input

File	Size	Notes
mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf	0.86 GiB / 0.92 GB	CLIP-style vision encoder + projector; required for images, pairs with any normal or MTP quant above

Qwythos inherits its vision tower from the Qwen3.5-9B base model — the vision path was frozen during SFT (training was text-only), so the vision behavior is identical to base Qwen3.5-9B's multimodal capability. The mmproj is interchangeable with any community-built Qwen3.5-9B mmproj-*.gguf.

---

Quick start

llama.cpp (llama-cli)

llama-cli \
  -m Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf \
  -p "Walk through the biochemistry of how organophosphate nerve agents inhibit acetylcholinesterase." \
  -n 8192 \
  --temp 0.6 --top-p 0.95 --top-k 20 --repeat-penalty 1.05 \
  -c 16384

Ollama

ollama run hf.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

LM Studio / jan / KoboldCpp

Drop any of the .gguf files into your runtime's model directory. Qwythos uses the standard Qwen3.5 chat template; modern GGUF runtimes load it automatically from the file.

llama.cpp with MTP draft speculation

llama-server \
  -m Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf \
  --spec-type draft-mtp \
  --spec-draft-n-max 6 \
  -c 16384 --port 8080

MTP support requires a recent llama.cpp build. If your runtime does not support MTP yet, use the normal v2 files above.

---

Vision (image input)

Qwythos supports image input out of the box. Download both a text quant and the mmproj-*.gguf file from this repo, then run with llama.cpp's multimodal CLI or server.

llama.cpp (llama-mtmd-cli)

llama-mtmd-cli \
  -m Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf \
  --mmproj mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf \
  --image ./photo.jpg \
  -p "Describe this image in detail." \
  --temp 0.6 --top-p 0.95 --top-k 20 \
  -c 16384

llama.cpp server (OpenAI-compatible API with images)

llama-server \
  -m Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf \
  --mmproj mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf \
  -c 16384 --port 8080

Then POST to /v1/chat/completions with an image URL or base64 payload — the standard OpenAI vision API shape works.

LM Studio

Load the text quant; LM Studio detects the matching mmproj-*.gguf in the same folder and enables the image-attach button automatically.

What vision unlocks

Since Qwythos inherits its vision tower unchanged from Qwen3.5-9B base, expect Qwen3.5-9B's documented vision capabilities: detailed image description, OCR (printed + handwritten), chart/table reading, UI/document understanding, basic spatial reasoning.

Honest note: the SFT used to produce Qwythos was text-only — we did not fine-tune the vision tower or train on any image-paired data. Image-grounded reasoning therefore inherits the base model's behavior; it has not been independently evaluated as part of this release. If your application is primarily vision-driven, validate on your own use case first.

---

Sampling recommendations

Qwythos is a reasoning model — every response opens with a <think>...</think> block before the final answer. Use these settings as defaults:

Parameter	Value
temperature	0.6
top_p	0.95
top_k	20
repeat_penalty	1.05
max_new_tokens	16384 (generous budget for <think> + answer)

These match Qwen3.5's official thinking-mode recommendations. Avoid greedy decoding and very-low-temperature sampling (T ≤ 0.3) — both can cause repetition loops on long reasoning generations.

---

Long context (1M tokens)

The GGUFs ship with YaRN rope-scaling baked in for a 1,048,576-token context window (4× extension over the 262k native).

To use the full 1M window in llama-cli, set -c 1010000 (or any context length up to that). For shorter prompts, lower -c to reduce KV-cache memory — at default settings llama.cpp will autosize.

A single H100/H200-class GPU comfortably handles 256k–512k; the full 1M typically needs tensor-parallel multi-GPU or aggressive KV-cache offload.

---

Capabilities (from the base model card)

• +34 pts MMLU, +30 pts gsm8k-strict, +19 pts gsm8k-flex vs. base Qwen3.5-9B under matched lm-eval-harness evaluation
• Native function calling per Qwen3.5's chat-template spec — emits <tool_call><function=NAME><parameter=NAME>VAL</parameter></function></tool_call> blocks ready for any tool-use loop
• Self-correcting with tools: in a 7-prompt tool-use harness (Python executor + DuckDuckGo search), Qwythos produced source-cited correct answers on 7/7, including 4/4 closed-book failure-modes from the original review
• Uncensored — engages seriously with technically demanding questions across cybersecurity, red-teaming, biology, pharmacology, and clinical medicine
• 1,048,576-token (1M) context — YaRN rope-scaling enabled by default

For full eval transcripts and per-task numbers, see the base model card's evals/ folder.

---

Limitations

• Reasoning model. Every answer opens with a <think> block; allow generous max_new_tokens and parse/strip <think>...</think> for end users.
• Use recommended sampling. Greedy / very-low-temp can cause repetition loops.
• Verify specifics in safety-critical contexts. Like all closed-book LLMs in this weight class, Qwythos can over-commit to specific identifiers (CVEs, hashcat modes, drug positions) it isn't certain about. Pair with retrieval or function calling in such deployments — the model uses tools cleanly when offered them.
• Uncensored — add your own application-level review/safety layer for end-user-facing deployments where that matters.

---

Stay in the loop

Sign up for the Empero newsletter at empero.org for releases, evals, and research notes.

Support / Donate

If this model helped you, consider supporting the project:

• BTC: bc1qx6zepu6sfkvshgdmc4ewu6pk6rpadvpgffpp7v
• LTC: ltc1qv2mefzps2vtjcpwfx8xxdrpplrcvltswm68r7x
• XMR: 42Dbm5xg5Nq26fdyzfEU7KBnAJfhi7Cvz5J2ex5CzHXkfKuNEJzYCcmJ1GTbgjFZ5MBx72sdG1G9239Cd6rsZfv4QeDkYJY

---

Provenance & licensing

Weights are released under Apache-2.0, inherited from the Qwen3.5-9B base. Shared for research and experimentation, as-is.

Acknowledgements

• Developed and released by Empero
• Base model: Qwen3.5-9B (Alibaba Qwen team)
• Quantization: llama.cpp (ggml-org)
• Vision projector (mmproj): inherited from Qwen3.5-9B (vision tower unchanged); F16 GGUF re-hosted with thanks to Unsloth for the original conversion
• HF model: empero-ai/Qwythos-9B-Claude-Mythos-5-1M