---
license: apache-2.0
language:
- en
library_name: gguf
pipeline_tag: text-generation
model_name: TurboQwen3.6
tags:
- gguf
- llama.cpp
- qwen
- qwen3.6
- mtp
- speculative-decoding
- turboquant
- tq3_4s
base_model:
- unsloth/Qwen3.6-27B-MTP-GGUF
model-index:
- name: TurboQwen3.6
  results: []
---

# TurboQwen3.6

**Canonical artifact:** `Qwen3.6-27B-MTP-TQ3_4S`

![TurboQwen3.6](thumbnail.png)

`TurboQwen3.6` is the public release name for the TurboQuant GGUF build of the Qwen3.6 27B MTP model line.

The exact file and runtime artifact name remains:

- `Qwen3.6-27B-MTP-TQ3_4S.gguf`

## Parent Model

- Upstream parent: `unsloth/Qwen3.6-27B-MTP-GGUF`
- Format conversion and TurboQuant packaging: `turbo-tan/llama.cpp-tq3`

This release is intended for the public TurboQuant runtime fork:

- `https://github.com/turbo-tan/llama.cpp-tq3`

It requires TQ3_4S runtime support and draft-MTP support. It is not expected to run correctly on stock `llama.cpp` builds that do not contain these extensions.

## Matching Projector

The multimodal projector is published separately so the main Hugging Face page stays anchored on the 27B text model:

- `https://huggingface.co/YTan2000/Qwen3.6-27B-MTP-TQ3_4S-mmproj`

## Files

- `Qwen3.6-27B-MTP-TQ3_4S.gguf` - main model, 13.39 GiB
- `mmproj.gguf` - matching multimodal projector, 0.87 GiB, hosted in the separate projector repo above
- `thumbnail.png` - model card image
- `benchmark.png` - benchmark summary image

## Recommended Runtime

Use flash attention at runtime and enable draft-MTP speculative decoding:

```bash
./build/bin/llama-server \
  -m Qwen3.6-27B-MTP-TQ3_4S.gguf \
  --mmproj mmproj.gguf \
  --alias Qwen3.6-27B-MTP-TQ3_4S.gguf \
  --host 127.0.0.1 --port 8080 \
  -c 32768 -np 1 -ngl 99 -fa on \
  -ctk q8_0 -ctv tq3_0 \
  --spec-type draft-mtp \
  --spec-draft-n-min 1 \
  --spec-draft-n-max 2 \
  --spec-draft-p-min 0.0 \
  --reasoning off --jinja
```

Important build note:

- `-fa on` above is the runtime flash-attention flag.
- Do not confuse it with the CMake build flag `GGML_CUDA_FA_ALL_QUANTS`.
- The validated fast release path uses runtime `-fa on` with `GGML_CUDA_FA_ALL_QUANTS=OFF`.

## Quick Smoke Test

For a smaller local smoke, reduce context to `4096`:

```bash
./build/bin/llama-server \
  -m Qwen3.6-27B-MTP-TQ3_4S.gguf \
  --mmproj mmproj.gguf \
  --alias Qwen3.6-27B-MTP-TQ3_4S.gguf \
  --host 127.0.0.1 --port 8096 \
  -c 4096 -np 1 -ngl 99 -fa on \
  -ctk q8_0 -ctv tq3_0 \
  --spec-type draft-mtp \
  --spec-draft-n-min 1 \
  --spec-draft-n-max 2 \
  --spec-draft-p-min 0.0 \
  --reasoning off --jinja --no-warmup
```

Then:

```bash
curl -s http://127.0.0.1:8096/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"Qwen3.6-27B-MTP-TQ3_4S.gguf","messages":[{"role":"user","content":"Write ONLY the word ok."}],"max_tokens":32,"temperature":0}'
```

Expected assistant content:

```text
ok
```

## Benchmark Summary

Local BenchLoop comparison on RTX 3090, using draft-MTP and the runtime settings above:

![Benchmark summary](benchmark.png)

| Metric | Result |
|---|---:|
| Overall score | 86.28 |
| EasyCode | 100.00% |
| Hard86 | 88.4% |
| Toolcall | 96.67% |
| Data extract | 90.97% |
| Instruct follow | 76.67% |
| Reason math | 73.33% |
| Generation speed | 44.80 tok/s |
| Size | 13.39 GiB |

The packaged benchmark summary image is included in this repo as `benchmark.png`.

## Notes

- This is an MTP release. Use `--spec-type draft-mtp` with `--spec-draft-n-max 2`.
- Use `--spec-draft-p-min 0.0` on the current TurboQuant runtime.
- Use `-ctk q8_0 -ctv tq3_0` for the validated release profile.
- If draft acceptance collapses to `0.00000` on long prompts, stop and check the runtime build and launch flags before benchmarking.

## License

Use is subject to the base model license and the license terms of the runtime components used to run the GGUF.