GraySoft
Download guIDE →
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

0xA50C1A1/Brightmere-14B-GGUF overview

GGUF quantizations of Brightmere 14B https://huggingface.co/0xA50C1A1/Brightmere 14B . | Link | Type | Size | |: |: | :| | GGUF https://huggingface.co/0xA50C1A…

transformersggufmistral-commonrproleplayuncensorednvfp4base_model:0xA50C1A1/Brightmere-14Bbase_model:quantized:0xA50C1A1/Brightmere-14Blicense:apache-2.0endpoints_compatibleregion:usimatrixconversational

Runs locally from ~7.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
800
Likes
0
Pipeline
—
Author
0xA50C1A1

Repository Files & Downloads

4 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Brightmere-14B-IQ4_NL-Mixed.ggufGGUFIQ4_NL8.72 GBDownload
Brightmere-14B-NVFP4.ggufGGUFGGUF8.88 GBDownload
Brightmere-14B-mmproj-Q8_0.ggufGGUFQ8_0458.4 MBDownload
imatrix.ggufGGUFGGUF7.1 MBDownload

Model Details

Model ID0xA50C1A1/Brightmere-14B-GGUF
Author0xA50C1A1
Pipeline—
Licenseapache-2.0
Base model0xA50C1A1/Brightmere-14B
Last modified2026-06-27T17:45:08.000Z

Model README

---

base_model: 0xA50C1A1/Brightmere-14B

library_name: transformers

license: apache-2.0

tags:

  • mistral-common
  • rp
  • roleplay
  • uncensored
  • nvfp4

---

GGUF quantizations of Brightmere-14B.

| Link | Type | Size |

|:-----|:-----|--------:|

| GGUF | Multimodal supplement (Q8_0) | 480 MB |

| GGUF | Mixed (IQ4_NL/Q6_K) | 9.4 GB |

| GGUF | NVFP4 | 9.5 GB |

Run 0xA50C1A1/Brightmere-14B-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models