---
license: apache-2.0
base_model:
- vvsotnikov/Qwen3.8-27B-0.9-Qwen3.6-27B-0.1
base_model_relation: quantized
library_name: llama.cpp
tags:
- gguf
- qwen
- llama.cpp
- quantized
- vvsotnikov
- Qwen3.8-27B-0.9-Qwen3.6-27B-0.1
---
# Qwen3.8-27B-0.9-Qwen3.6-27B-0.1-GGUF

GGUF quantizations of: 
[vvsotnikov/Qwen3.8-27B-0.9-Qwen3.6-27B-0.1](https://huggingface.co/vvsotnikov/Qwen3.8-27B-0.9-Qwen3.6-27B-0.1)

# Source Model Card

## Qwen3.8-27B 0.9 + Qwen3.6-27B 0.1

This checkpoint is a direct linear interpolation of the complete upstream
checkpoints:

```text
merged = 0.1 * Qwen/Qwen3.6-27B + 0.9 * Qwen/Qwen3.8-27B
```

### Merge details

- Method: element-wise linear interpolation in float32, cast to the original
  bfloat16 dtype after each tensor is merged
- Tensors merged: 1,199, including the embedded `mtp.*` drafter
  tensors and vision tower
- Shard layout, configuration, tokenizer, processor, and chat template:
  `Qwen/Qwen3.8-27B`
- `Qwen/Qwen3.6-27B` revision: `6a9e13bd6fc8f0983b9b99948120bc37f49c13e9`
- `Qwen/Qwen3.8-27B` revision: `1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0`
- Quantization: none

The two source checkpoints have identical tensor names, shapes, dtypes, and
model configuration; their configs differ only in the recorded Transformers
version. The newer `Qwen/Qwen3.8-27B` non-weight files are used because it has the
larger merge coefficient.

### License and use

Both source checkpoints are Apache-2.0. Their upstream model cards describe
capabilities, limitations, and the expected `qwen3_5` runtime support.