reka flash 3 GGUF QX k Bf16 needs about 16.8 GB of memory at Q4_K (a 15.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 12.6 GB (Q3_K) to 23.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
reka flash 3 GGUF QX k Bf16 is a 20.9B-parameter Reka model in GGUF format, quantized by Rombo-Org. Its trained context length is 32K tokens. The repository has 4 quant files, from 12.6 GB (Q3_K) to 23.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K | 12.6 GB | 14.2 GB | Too big | Get file → | |
| Q4_K | 15.2 GB | 16.8 GB | Too big | Get file → | |
| Q5_K | 17.2 GB | 18.8 GB | Too big | Get file → | |
| Q8_0 | 23.4 GB | 25.0 GB | Too big | Get file → |
What GPU do you need for reka flash 3 GGUF QX k Bf16?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q3_K (12.6 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K (17.2 GB file, about 18.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (23.4 GB file, about 25.0 GB in use).
Which reka flash 3 GGUF QX k Bf16 quant should you choose?
Q4_K (15.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q3_K at 12.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about reka flash 3 GGUF QX k Bf16
How much VRAM does reka flash 3 GGUF QX k Bf16 need?
About 16.8 GB at Q4_K with an 8K context window. That is the 15.2 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 reka flash 3 GGUF QX k Bf16 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of reka flash 3 GGUF QX k Bf16 GGUF?
It depends on the quant: Q3_K is 12.6 GB, Q4_K is 15.2 GB, Q5_K is 17.2 GB, Q8_0 is 23.4 GB.
What context length does reka flash 3 GGUF QX k Bf16 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.
Where can I download reka flash 3 GGUF QX k Bf16 GGUF?
The files are on Hugging Face in the Rombo-Org/reka-flash-3-GGUF_QX_k_Bf16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does reka flash 3 GGUF QX k Bf16 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.