Model index / GLM / GLM-4.7-Flash-abliterated
GLM / MODEL PROFILE
GLM-4.7-Flash-abliterated
huihui-ai · Published release · Abliteration · GGUF / MLX / Transformers / FP8
Model source
Published by huihui-ai on Hugging Face. This index organizes public repository metadata for discovery and comparison. Refer to the publisher and independent testing for actual model behavior.
Declared base model
Hardware and context
The parameter count cannot be determined from current metadata, so no VRAM estimate is provided. KV cache, context length, multimodal components and concurrency increase actual memory usage.
Context length: Not stated in public metadata. Please consult the model card.
Download sources and quantized variants
14 repositories| HUGGING FACE REPOSITORY | Format | 30-day downloads | Declared license |
|---|---|---|---|
| mradermacher/Huihui-GLM-4.7-Flash-abliterated-i1-GGUF ↗ | GGUF | 14.6K | mit |
| mradermacher/Huihui-GLM-4.7-Flash-abliterated-GGUF ↗ | GGUF | 13.4K | mit |
| bloopez/Huihui-GLM-4.7-Flash-abliterated-BF16-GGUF ↗ | GGUF | 1.7K | mit |
| huihui-ai/Huihui-GLM-4.7-Flash-abliterated-mlx-4bit ↗ | MLX | 1.6K | mit |
| huihui-ai/Huihui-GLM-4.7-Flash-abliterated ↗ | Transformers | 1.2K | mit |
| cognitivers/GLM-4.7-Flash-abliterated-12GB-GGUF ↗ | GGUF | 1.1K | mit |
| cs2764/Huihui-GLM-4.7-Flash-abliterated-Q6_K-GGUF ↗ | GGUF | 642 | mit |
| mlx-community/glm-4.7-flash-abliterated-8bit ↗ | MLX | 189 | Not stated |
| mlx-community/GLM-4.7-Flash-abliterated-mxfp8 ↗ | MLX | 184 | mit |
| cs2764/Huihui-GLM-4.7-Flash-abliterated-mlx-8Bit ↗ | MLX | 97 | mit |
| tutuchen2000/Huihui-GLM-4.7-Flash-abliterated-GGUF ↗ | GGUF | 93 | mit |
| cs2764/Huihui-GLM-4.7-Flash-abliterated-Q8_0-GGUF ↗ | GGUF | 61 | mit |
| operationrange/GLM-4.7-Flash-abliterated-FP8-Dynamic ↗ | FP8 | 33 | mit |
| DevQuasar/huihui-ai.Huihui-GLM-4.7-Flash-abliterated-GGUF ↗ | GGUF | 0 | Not stated |
Uncensored is a publisher description, not a guarantee of zero refusals, capability, accuracy or safety. This index does not measure refusal rates or performance benchmarks.
More from this family
More GLM →GLMSize not stated ↗
orcarouter_GLM-5.3-Flash-Uncensored
BoldingBuilds
↓ 629K ♡ 784VRAM unknown ↗
GLMSize not stated ↗
GLM-5.3-CYBERSECURITY
dealignai
↓ 124.8K ♡ 739VRAM unknown ↗
GLMSize not stated ↗
GLM-5.3-Flash-UNCENSORED
AliceThirty
↓ 94.3K ♡ 280VRAM unknown ↗
GLMSize not stated ↗
GLM-5.3-Flash-abliterated
huihui-ai
↓ 50.3K ♡ 319VRAM unknown ↗