DeciLM 6b Instruct needs about 8.2 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.3 GB (IQ1_S) to 4.7 GB (Q6_K).
DeciLM 6b Instruct – 5.72B parameter instruction model
DeciLM 6b Instruct is a 5.72B parameter auto‑regressive language model fine‑tuned on OpenOrca for short‑form instruction following. It uses a deci architecture with variable Grouped‑Query Attention. The model is licensed under the Llama 2 Community License Agreement.
Good at
- Instruction following in English
- Short‑form dialogue
- Fine‑tuning for other languages
Limits
- No vision support
- No safety alignment or RLHF
- Context length limited to 4096 tokens
Best for
- Chatbot prototypes
- Instruction‑based research
- Fine‑tuning for niche domains
Who it’s for. Developers and researchers who need a lightweight, instruction‑oriented LLM for English. The model can be further fine‑tuned for other languages or specialized tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.3 GB | 3.9 GB | Fits | Get file → | |
| IQ1_M | 1.4 GB | 4.0 GB | Fits | Get file → | |
| IQ2_XXS | 1.6 GB | 4.2 GB | Fits | Get file → | |
| IQ2_XS | 1.7 GB | 4.4 GB | Fits | Get file → | |
| IQ2_S | 1.8 GB | 4.5 GB | Fits | Get file → | |
| IQ2_M | 2.0 GB | 4.6 GB | Fits | Get file → | |
| Q2_K_S | 2.0 GB | 4.6 GB | Fits | Get file → | |
| Q2_K | 2.1 GB | 4.8 GB | Fits | Get file → | |
| IQ3_XXS | 2.2 GB | 4.9 GB | Fits | Get file → | |
| IQ3_XS | 2.4 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_S | 2.5 GB | 5.2 GB | Fits | Get file → | |
| IQ3_S | 2.5 GB | 5.2 GB | Fits | Get file → | |
| IQ3_M | 2.6 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_M | 2.8 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_L | 3.0 GB | 5.7 GB | Fits | Get file → | |
| IQ4_XS | 3.1 GB | 5.7 GB | Fits | Get file → | |
| IQ4_NL | 3.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 3.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_S | 3.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 6.1 GB | Fits | Get file → | |
| Q4_1 | 3.6 GB | 6.2 GB | Fits | Get file → | |
| Q5_K_S | 3.9 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 4.0 GB | 6.7 GB | Fits | Get file → | |
| Q6_K | 4.7 GB | 7.3 GB | Tight | Get file → |
For 8 GB VRAM use IQ1_S (1.27 GB file, 6.1 GB memory) or IQ1_M (1.38 GB file, 6.2 GB memory). With 12 GB VRAM, Q4_K_M (3.44 GB file, 8.2 GB memory) or Q5_K_M (4.05 GB file, 8.8 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q6_K (4.69 GB file, 9.5 GB memory).
What GPU do you need for DeciLM 6b Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is IQ4_NL (3.3 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (4.7 GB file, about 9.5 GB in use).
Which DeciLM 6b Instruct quant should you choose?
Q4_K_M is the usual starting point for DeciLM 6b Instruct: it balances file size and quality well. Here it is a 3.4 GB file.
If memory is tight, the smallest file is IQ1_S at 1.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeciLM 6b Instruct
How much VRAM does DeciLM 6b Instruct need?
About 8.2 GB at Q4_K_M with an 8K context window. That is the 3.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run DeciLM 6b Instruct on an 8 GB GPU?
Yes, with IQ4_NL: the 3.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeciLM 6b Instruct GGUF?
It depends on the quant: IQ1_S is 1.3 GB, IQ1_M is 1.4 GB, IQ2_XXS is 1.6 GB, IQ2_XS is 1.7 GB, IQ2_S is 1.8 GB, IQ2_M is 2.0 GB and 18 more.
What context length does DeciLM 6b Instruct support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download DeciLM 6b Instruct GGUF?
The files are on Hugging Face in the mradermacher/DeciLM-6b-instruct-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does DeciLM 6b Instruct use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run DeciLM 6b Instruct on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quants; they require about 6.1–6.2 GB VRAM at 8k context.
Does the model support vision tasks?
No, DeciLM 6b Instruct is a text‑only model.
Is the model safe for production use?
The model has not been aligned for safety or trained with RLHF; use with caution.