No official torrent yet β requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF
All models by empero-ai β
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.
If you don't know which to pick, Q4_K_M is the right starting point β it's the smallest practical quant with good quality preservation.
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.
Qwythos inherits its vision tower from the Qwen3.5-9B base model β 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.
llama-cli)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.
MTP support requires a recent llama.cpp build. If your runtime does not support MTP yet, use the normal fixed v3 files above.
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-mtmd-cli)Then POST to /v1/chat/completions with an image URL or base64 payload β the standard OpenAI vision API shape works.
Load the text quant; LM Studio detects the matching mmproj-*.gguf in the same folder and enables the image-attach button automatically.
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 β 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.
Qwythos is a reasoning model β every response opens with a <think>...</think> block before the final answer. Use these settings as defaults:
These match Qwen3.5's official thinking-mode recommendations. Avoid greedy decoding and very-low-temperature sampling (T β€ 0.3) β both can cause repetition loops on long reasoning generations.
The GGUFs ship with YaRN rope-scaling baked in for a 1,048,576-token context window (4Γ 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 β at default settings llama.cpp will autosize.
A single H100/H200-class GPU comfortably handles 256kβ512k; the full 1M typically needs tensor-parallel multi-GPU or aggressive KV-cache offload.
<tool_call><function=NAME><parameter=NAME>VAL</parameter></function></tool_call> blocks ready for any tool-use loopFor full eval transcripts and per-task numbers, see the base model card's evals/ folder.
<think> block; allow generous max_new_tokens and parse/strip <think>...</think> for end users.Sign up for the Empero newsletter at empero.org for releases, evals, and research notes.
If this model helped you, consider supporting the project:
bc1qx6zepu6sfkvshgdmc4ewu6pk6rpadvpgffpp7vltc1qv2mefzps2vtjcpwfx8xxdrpplrcvltswm68r7x42Dbm5xg5Nq26fdyzfEU7KBnAJfhi7Cvz5J2ex5CzHXkfKuNEJzYCcmJ1GTbgjFZ5MBx72sdG1G9239Cd6rsZfv4QeDkYJYWeights are released under Apache-2.0, inherited from the Qwen3.5-9B base. Shared for research and experimentation, as-is.
mmproj): inherited from Qwen3.5-9B (vision tower unchanged); F16 GGUF re-hosted with thanks to Unsloth for the original conversionllama-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 16384ollama run hf.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_Mllama-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 8080llama-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 16384llama-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