Qwythos-9B-v2-GGUF

GGUF quantizations of **[empero-ai/Qwythos-9B-v2](https://huggingface.co/empero-ai/Qwythos-9B-v2)** for [llama.cpp](https://github.com/ggml-org/llama.cpp), Ollama, LM Studio, jan, KoboldCpp, and other GGUF runtimes. **Qwythos-9B-v2 is the new and improved Qwythos** — all the deep chain-of-thought reasoning of the base Qwythos, with the **looping behavior fixed**. The looping/degeneration that showed up under greedy or low-temperature decoding is trained out (**6.7% → 0%**), the native **MTP head is restored**, and the identity prompt is cleaned up — while knowledge and reasoning are held at (or above) the base Qwythos level. The fix uses **FTPO (Final-Token Preference Optimization)**: the exact token that *starts* a repetition loop is identified and the model is gently trained to prefer coherent alternatives at that one position, leaving the rest of the distribution — and therefore its knowledge and reasoning — untouched. For full training details, evaluation numbers, and sample generations, see the **[base model card](https://huggingface.co/empero-ai/Qwythos-9B-v2)**. - 🔁 **Looping behavior eliminated** — repetition under greedy / low-temp decoding dropped **6.7% → 0%**. **Greedy decoding is now safe** — you no longer need `repeat-penalty` as a band-aid. - 🧩 **MTP head restored** — the native multi-token-prediction module is back in the `-MTP-` files, so speculative-decoding (`--spec-type draft-mtp`) works. - 🧠 **Reasoning preserved** — MMLU / GSM8K / GPQA / ARC held at or above the base Qwythos level (see the model card). - 🪪 **Cleaner identity** — states who it is once, only when asked. - 🔓 Still intentionally **uncensored**, still **1M-token context** (YaRN), still **multimodal-capable** (Qwen3.5 vision tower). If you don't know which to pick, **Q4_K_M is the right starting point.** These embed the restored Qwen3.5-compatible MTP head. Use them with llama.cpp builds that support MTP draft speculation (`--spec-type draft-mtp`). The MTP matrices are retained at **Q8_0** in every quantized variant. The vision tower is inherited **unchanged from Qwen3.5-9B** — it was frozen through both the base Qwythos SFT and the v2 FTPO fine-tune, so image behavior matches base Qwen3.5-9B. This mmproj is interchangeable with any Qwen3.5-9B `mmproj-*.gguf`. Qwythos is a **hybrid** model — a 3:1 mix of Gated-DeltaNet linear-attention (SSM) blocks and full-attention blocks. The linear-attention state tensors are disproportionately sensitive to low-bit quantization, so the K-quants here keep them at higher precision than the surrounding weights: The remaining SSM state tensors (`ssm_a`, `ssm_conv1d`, `ssm_dt`, `ssm_norm`) are kept at **F32** by the converter. This preserves the hybrid/SSM blocks for a small (~2–4%) increase in file size over a flat K-quant. `Q8_0` and `BF16` are uniform and need no overrides. llama-cli \ -m Qwythos-9B-v2-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 Because v2's looping is trained out, `--repeat-penalty` is now optional and **greedy decoding (`--temp 0`) stays coherent.** ollama run hf.co/empero-ai/Qwythos-9B-v2-GGUF:Q4_K_M Drop any `.gguf` into your runtime's model directory. Qwythos uses the standard Qwen3.5 chat template; modern GGUF runtimes load it automatically from the file. llama-server \ -m Qwythos-9B-v2-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 doesn't support MTP yet, use the normal files. Download a text quant **plus** the `mmproj-*.gguf`, then run llama.cpp's multimodal CLI/server: llama-mtmd-cli \ -m Qwythos-9B-v2-Q4_K_M.gguf \ --mmproj mmproj-Qwythos-9B-v2-BF16.gguf \ --image ./photo.jpg \ -p "Describe this image in detail." \ --temp 0.6 --top-p 0.95 --top-k 20 -c 16384 **Honest note:** all Qwythos training (base SFT and v2 FTPO) was **text-only** — the vision tower was never fine-tuned, so image-grounded reasoning inherits base Qwen3.5-9B behavior and has not been independently evaluated for this release. Qwythos is a reasoning model — every response opens with a `<think>...</think>` block before the answer. Unlike the base Qwythos, **v2 does not loop under greedy / low-temperature decoding** — you can use `--temp 0` for deterministic runs without repetition. The 0.6-temperature settings above still match Qwen3.5's official thinking-mode recommendations for best quality. The GGUFs ship with YaRN rope-scaling baked in for a **1,048,576-token context window** (4× the 262,144 native). Set `-c` up to `1048576`; lower it to reduce KV-cache memory for shorter prompts. A single H100/H200-class GPU comfortably handles 256k–512k; the full 1M typically needs multi-GPU or aggressive KV-cache offload. - Converted and quantized with **llama.cpp** (`convert_hf_to_gguf.py`, `llama-quantize`), architecture `qwen35`, GGUF v3. - MTP variants: default conversion (33-block, `nextn_predict_layers = 1`, 15 MTP tensors, MTP matrices pinned Q8_0). Normal variants: `--no-mtp` (32-block trunk-only). mmproj: `--mmproj --outtype bf16`. - Hybrid-precision overrides applied per the table above. - Structurally verified (arch / block count / `nextn` key / per-tensor types) and smoke-tested for load + coherent generation. - `shasum -a 256 -c SHA256SUMS` covers all 11 artifacts. Apache-2.0, inherited from Qwen3.5-9B. Shared for research and experimentation, as-is. - Developed and released by **Empero AI** - Base model: **Qwen3.5-9B** (Alibaba Qwen team) - Looping fixed with **FTPO (Final-Token Preference Optimization)** - Quantization: **llama.cpp** (ggml-org) - HF model: [empero-ai/Qwythos-9B-v2](https://huggingface.co/empero-ai/Qwythos-9B-v2)