---
base_model: MichaelAnthony/qwen-3.5-0.8b-Hedgehog
library_name: gguf
tags:
- gguf
- qwen3.5
- rag
- document-extraction
- simplerag
---

# qwen-3.5-0.8b-Hedgehog GGUF r5

GGUF builds of the accepted r5 starter release. Every file was inspected as a
24-block `qwen35` model with 320 tensors and independently loaded through
llama.cpp ROCm. All four formats produced exact 7/7-field JSON in the release
invoice smoke test.

| File | Size | SHA-256 |
|---|---:|---|
| `qwen-3.5-0.8b-Hedgehog.F16.gguf` | 1,516,744,064 | `b3fb5a844cf7f7d2024916e366e767e89f4ca664c008a3528a919787b546dbf0` |
| `qwen-3.5-0.8b-Hedgehog.Q4_K_M.gguf` | 529,296,768 | `04fa8f6c59820043a806b695e5238d91980388615d2105ded5d87aee38306442` |
| `qwen-3.5-0.8b-Hedgehog.Q6_K.gguf` | 629,743,488 | `4b2279c6009edb9590867e204f86537a55ded264f4f396f229165f3159d43186` |
| `qwen-3.5-0.8b-Hedgehog.Q8_0.gguf` | 811,842,944 | `009c05a62bb642840f79efdf802a73d79b1a1070d10913a86c4ca400b344f070` |

Use `Q6_K`; `Q6_K_0` is not a supported quantization name in the verified
llama.cpp toolchain. For deterministic extraction, use temperature 0 and
disable thinking. See the main Transformers repository for the complete r5
evaluation and known limitations.