Downloads · 30 days
19
4% of all-time downloads
Nanbeige4.1-3B-imatrix-GGUF
liodon-ai/Nanbeige4.1-3B-imatrix-GGUF
Nanbeige4.1-3B-imatrix-GGUF is a text generation model from liodon-ai. Use it when you need the model to write or continue text. The card lists the license as other.
GGUF quantizations of Nanbeige/Nanbeige4.1-3B, published by Liodon AI.
All-time downloads
518
Public
Repo size
18.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf18.3 GB · 100%
At a glance
- Task
- Text Generation
- License
- other
- Access
- Public
- Created
- Jul 20, 2026
- Updated
- Jul 20, 2026
- SHA
- d18b4229
Try a prompt
Base models
Model card
From the Hugging Face model README
Nanbeige4.1-3B — iMatrix GGUF
GGUF quantizations of Nanbeige/Nanbeige4.1-3B, published by Liodon AI.
Quick Start
llama.cpp
llama-cli -hf liodon-ai/Nanbeige4.1-3B-imatrix-GGUF:Q4_K_M
Ollama
ollama run hf.co/liodon-ai/Nanbeige4.1-3B-imatrix-GGUF:Q4_K_M
LM Studio / Jan — search liodon-ai/Nanbeige4.1-3B-imatrix-GGUF and pick your quant.
Quants
| Quant | Size | VRAM est. | Notes |
|---|---|---|---|
IQ2_M | 1.51 GB | ~2 GB | 2-bit, iMatrix — smallest usable |
IQ3_M | 1.91 GB | ~2 GB | 3-bit, iMatrix — great quality/size tradeoff |
IQ4_XS | 2.22 GB | ~3 GB | 4-bit extra-small, iMatrix |
Q4_K_M | 2.44 GB | ~3 GB | 4-bit, iMatrix-calibrated (recommended) |
Q5_K_M | 2.83 GB | ~3 GB | 5-bit, iMatrix-calibrated |
Q6_K | 3.23 GB | ~4 GB | 6-bit, iMatrix-calibrated, near-lossless |
Q8_0 | 4.18 GB | ~5 GB | 8-bit, essentially lossless |
What is iMatrix?
Standard quantization treats all weights equally. iMatrix runs 128 calibration chunks through the full-precision model to find which weights matter most, then allocates more precision where it counts. At Q2/Q3/Q4 this means noticeably better coherence and instruction-following — same file size, better output.
Calibration: 2M tokens of WikiText-103.
Also see plain (non-iMatrix) quants:
liodon-ai/Nanbeige4.1-3B-GGUF
Source
- Model: Nanbeige/Nanbeige4.1-3B
- License: other
Quantized by Liodon AI
- Task
- Text Generation
- License
- other
- Created
- Jul 20, 2026
- Updated
- Jul 20, 2026