Llama-3-13B-Instruct-ft needs about 10.3 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.0 GB (Q2_K) to 13.9 GB (Q8_0).
Llama‑3‑13B‑Instruct‑ft – a 13 B finetuned Llama‑3 model
Llama‑3‑13B‑Instruct‑ft is a QLoRA finetune of a merged Llama‑3‑13B‑Instruct base. It was trained on 8192 context tokens and is designed for instruction following. The model is available in multiple GGUF quantizations.
Good at
- Instruction following
- Story writing
- Role‑playing
Limits
- No vision support
- Math reliability limited
- Requires 8192 context
Best for
- Chatbots with 8‑k context
- Creative writing prompts
- RP sessions
Who it’s for. Developers building instruction‑based chat applications or creative writing tools. The model is suitable for users who need a mid‑size Llama‑3 variant with fine‑tuned instruction handling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.0 GB | 7.4 GB | Tight | Get file → | |
| IQ3_XS | 5.6 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_S | 5.8 GB | 8.2 GB | Too big | Get file → | |
| IQ3_S | 5.9 GB | 8.2 GB | Too big | Get file → | |
| IQ3_M | 6.0 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_M | 6.4 GB | 8.8 GB | Too big | Get file → | |
| Q3_K_L | 7.0 GB | 9.3 GB | Too big | Get file → | |
| IQ4_XS | 7.2 GB | 9.5 GB | Too big | Get file → | |
| Q4_K_S | 7.5 GB | 9.9 GB | Too big | Get file → | |
| Q4_K_M | 7.9 GB | 10.3 GB | Too big | Get file → | |
| Q5_K_S | 9.0 GB | 11.4 GB | Too big | Get file → | |
| Q5_K_M | 9.3 GB | 11.6 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 13.1 GB | Too big | Get file → | |
| Q8_0 | 13.9 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 5.02 GB, memory 7.4 GB). For 12 GB VRAM, Q4_K_M (file size 7.92 GB, memory 10.3 GB) is a good balance. For 16 GB VRAM, Q5_K_M (file size 9.27 GB, memory 11.6 GB) offers higher quality.
What GPU do you need for Llama-3-13B-Instruct-ft?
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 IQ3_XS (5.6 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (9.3 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (10.7 GB file, about 13.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.9 GB file, about 16.2 GB in use).
Which Llama-3-13B-Instruct-ft quant should you choose?
Q4_K_M is the usual starting point for Llama-3-13B-Instruct-ft: it balances file size and quality well. Here it is a 7.9 GB file.
The Q8_0 file is 13.9 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 5.0 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 Llama-3-13B-Instruct-ft
How much VRAM does Llama-3-13B-Instruct-ft need?
About 10.3 GB at Q4_K_M with an 8K context window. That is the 7.9 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 Llama-3-13B-Instruct-ft on an 8 GB GPU?
Yes, with IQ3_XS: the 5.6 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama-3-13B-Instruct-ft GGUF?
It depends on the quant: Q2_K is 5.0 GB, IQ3_XS is 5.6 GB, Q3_K_S is 5.8 GB, IQ3_S is 5.9 GB, IQ3_M is 6.0 GB, Q3_K_M is 6.4 GB and 8 more.
What context length does Llama-3-13B-Instruct-ft support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.8 GB at 8K and 1.8 GB at 8K.
Where can I download Llama-3-13B-Instruct-ft GGUF?
The files are on Hugging Face in the mradermacher/Llama-3-13B-Instruct-ft-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 Llama-3-13B-Instruct-ft use?
Hugging Face lists the license as llama3. 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 this model on 8 GB VRAM?
Yes, the Q2_K quant requires 7.4 GB memory at 8k context, which fits 8 GB VRAM with some headroom.
Does this model support vision tasks?
No, the model has no vision capabilities.
What context length can it reliably use?
It was finetuned on 8192 tokens and is reliable up to 32k with RoPE.