llm-compiler-13b-ftd needs about 13.2 GB of memory at IQ3_M (a 6.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 2.9 GB (IQ1_S) to 26.0 GB.
13B Llama model quantized for efficient inference
llm-compiler-13b-ftd is a 13B parameter Llama model quantized with IMatrix and common quants. It supports a 16384 token context and is available in multiple GGUF quantizations. The model is released under an other license.
Good at
- Large context handling
- Efficient inference on GPUs
- Support for multiple quant levels
Limits
- No vision support
- License not specified
- Requires 8k context for memory estimates
Best for
- Chatbots needing long context
- Fine‑tuning on custom data
- Low‑latency inference
Who it’s for. Developers building LLM applications that need a balance between performance and memory usage. The model is suitable for those who can manage GGUF files and use llama.cpp for inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.9 GB | 10.1 GB | Too big | Get file → | |
| IQ1_M | 3.1 GB | 10.3 GB | Too big | Get file → | |
| IQ2_XXS | 3.5 GB | 10.7 GB | Too big | Get file → | |
| IQ2_XS | 3.9 GB | 11.1 GB | Too big | Get file → | |
| IQ2_S | 4.2 GB | 11.4 GB | Too big | Get file → | |
| Q2_K_S | 4.4 GB | 11.6 GB | Too big | Get file → | |
| IQ2_M | 4.5 GB | 11.7 GB | Too big | Get file → | |
| Q2_K | 4.9 GB | 12.1 GB | Too big | Get file → | |
| IQ3_XXS | 5.0 GB | 12.2 GB | Too big | Get file → | |
| IQ3_XS | 5.4 GB | 12.6 GB | Too big | Get file → | |
| IQ3_S | 5.7 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_S | 5.7 GB | 12.9 GB | Too big | Get file → | |
| IQ3_M | 6.0 GB | 13.2 GB | Too big | Get file → | |
| Q3_K | 6.3 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_L | 6.9 GB | 14.1 GB | Too big | Get file → | |
| IQ4_XS | 7.0 GB | 14.2 GB | Too big | Get file → | |
| IQ4_NL | 7.4 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_S | 7.4 GB | 14.6 GB | Too big | Get file → | |
| Q4_K | 7.9 GB | 15.1 GB | Too big | Get file → | |
| Q5_K_S | 9.0 GB | 16.2 GB | Too big | Get file → | |
| Q5_K | 9.2 GB | 16.4 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 17.9 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 21.0 GB | Too big | Get file → | |
| BF16 | 26.0 GB | 33.2 GB | Too big | Get file → | |
| — | 26.0 GB | 33.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 2.9 GB, memory 10.1 GB) or IQ1_M (3.14 GB, 10.3 GB). With 12 GB VRAM, IQ2_S (4.2 GB, 11.4 GB) or Q2_K (4.85 GB, 12.1 GB) are suitable. For 16 GB VRAM, Q5_K_S (8.97 GB, 16.2 GB) or Q5_K (9.23 GB, 16.4 GB) provide a good trade‑off.
What GPU do you need for llm-compiler-13b-ftd?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ2_M (4.5 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K (7.9 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (26.0 GB file, about 33.2 GB in use).
Which llm-compiler-13b-ftd quant should you choose?
IQ3_M (6.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ1_S at 2.9 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 llm-compiler-13b-ftd
How much VRAM does llm-compiler-13b-ftd need?
About 13.2 GB at IQ3_M with an 8K context window. That is the 6.0 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 llm-compiler-13b-ftd on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llm-compiler-13b-ftd GGUF?
It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.2 GB, Q2_K_S is 4.4 GB and 19 more.
What context length does llm-compiler-13b-ftd support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 6.7 GB at 8K and 13.4 GB at 16K.
Where can I download llm-compiler-13b-ftd GGUF?
The files are on Hugging Face in the legraphista/llm-compiler-13b-ftd-IMat-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 llm-compiler-13b-ftd use?
Hugging Face lists the license as other. 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?
Use IQ1_S or IQ1_M quantizations; memory estimates are around 10 GB at 8k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What is the context length of this model?
The model supports a 16384 token context length.