Qwen2.5 Bakeneko 32B Instruct V2
Bakeneko Instruct V2 is a distinct instruction release. Its official GGUF card identifies the V2 parent and labels the model as an instruction merge with QwQ Bakeneko.
The available card establishes the release boundary
The GGUF package uses llama.cpp. Its card links the V2 parent for architecture and training details; it does not itself establish a complete training recipe. V2 formats belong to this one release.Qwen2.5 Bakeneko 32B Instruct V2 official model card
Compare equivalent weight formats where possible
Practical guidance. A comparison between V1 full-precision weights and V2 quantized weights mixes training and numerical changes. Use matched formats or report the precision difference alongside the results.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | qwen2.5-bakeneko-32b-instruct-v2qwen2.5-bakeneko-32b-instruct-v2-awqqwen2.5-bakeneko-32b-instruct-v2-ggufqwen2.5-bakeneko-32b-instruct-v2-gptq-int8qwen2.5-bakeneko-32b-instruct-v2-gptq-int4 |
| License | Apache 2.0 is declared by the official GGUF card.Qwen2.5 Bakeneko 32B Instruct V2 official model card |
| Verified access | Official GGUF, AWQ and GPTQ repositories remain listed. The unquantized parent repository could not be accessed in this review.Qwen2.5 Bakeneko 32B Instruct V2 official model card |
Related models
- Qwen2.5 Bakeneko 32B Instruct
rinna · Bakeneko
Bakeneko Instruct combines the Japanese-adapted base with Qwen2.5's instruction chat vector and Simple Preference Optimization, or SimPO.
Launch date not confirmedDownloadable - QwQ Bakeneko 32B
rinna · Bakeneko
QwQ Bakeneko 32B combines the Japanese-adapted Bakeneko base with a reasoning chat vector from QwQ-32B, followed by ORPO.
Launch date not confirmedDownloadable