Kroma v0.3.1 Turbo OPD needs about 10.4 GB of memory at Q4_K_M (a 8.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 6.0 GB (Q2_K) to 11.9 GB (Q6_K).
Kroma v0.3.1 Turbo OPD – a 12.8B flux model quantized for efficient inference
Kroma v0.3.1 Turbo OPD is a 12.8B flux model distilled on‑policy. It retains the original distribution while offering Turbo speed. The model is available in multiple GGUF quantizations for different memory budgets.
Good at
- Fast generation with Turbo settings
- On‑policy distillation preserves prompt quality
- Compatible with ComfyUI Krea 2 workflow
Limits
- No vision support in this text‑only quantized version
- Requires Krea 2 text encoder and VAE
- License is MIT but not all components are open
Best for
- Low‑latency text generation
- Fine‑tuning LoRAs on the base model
- Running in ComfyUI with Turbo sampling
Who it’s for. Developers and researchers who need a fast, on‑policy distilled flux model for text generation. The model works best when paired with the Krea 2 text encoder and VAE in a ComfyUI environment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 6.0 GB | 7.2 GB | Fits | Get file → | |
| Q3_K_M | 7.2 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_S | 7.2 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_M | 8.8 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_S | 8.8 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_M | 10.3 GB | 12.1 GB | Too big | Get file → | |
| Q6_K | 11.9 GB | 13.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 8.81 GB, estimated memory 10.4 GB). For 12 GB VRAM, Q5_K_M (10.33 GB, 12.1 GB). For 16 GB VRAM, Q6_K (11.94 GB, 13.9 GB). Lower quants such as Q2_K or Q3_K_M provide smaller file sizes but higher memory usage.
What GPU do you need for Kroma v0.3.1 Turbo OPD?
These figures add the file size, an fp16 KV cache at an 8K context window 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 Q2_K (6.0 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (8.8 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.9 GB file, about 13.9 GB in use).
Which Kroma v0.3.1 Turbo OPD quant should you choose?
Q4_K_M is the usual starting point for Kroma v0.3.1 Turbo OPD: it balances file size and quality well. Here it is a 8.8 GB file.
If memory is tight, the smallest file is Q2_K at 6.0 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 Kroma v0.3.1 Turbo OPD
How much VRAM does Kroma v0.3.1 Turbo OPD need?
About 10.4 GB at Q4_K_M with an 8K context window. That is the 8.8 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 Kroma v0.3.1 Turbo OPD on an 8 GB GPU?
Yes, with Q2_K: the 6.0 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kroma v0.3.1 Turbo OPD GGUF?
It depends on the quant: Q2_K is 6.0 GB, Q3_K_M is 7.2 GB, Q3_K_S is 7.2 GB, Q4_K_M is 8.8 GB, Q4_K_S is 8.8 GB, Q5_K_M is 10.3 GB and 1 more.
Where can I download Kroma v0.3.1 Turbo OPD GGUF?
The files are on Hugging Face in the Abiray/Kroma-v0.3.1-Turbo-OPD-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 Kroma v0.3.1 Turbo OPD 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 Kroma v0.3.1 Turbo OPD on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 10.4 GB of VRAM at 8k context.
Does this model support image generation?
No, the provided GGUF files are text‑only and do not include vision capabilities.
What sampler is recommended?
Use euler sampler with simple or sgm_uniform scheduler and a shift of ~1.15 for best results.