Crystal 31B RL needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.0 GB to 25.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Crystal 31B RL – a 30.7B Gemma4 role‑play model
Crystal 31B RL is a 30.7B parameter Gemma4 model trained for role‑play, reasoning, and tool use. It supports multiple languages and was fine‑tuned with style SFT and on‑policy RL. The model is released under the apache‑2.0 license.
Good at
- role‑play in multiple languages
- reasoning tasks
- tool‑based interactions
Limits
- trained context 262144 tokens
- no vision support
- requires large VRAM for full precision
Best for
- interactive storytelling
- character dialogue generation
- multilingual role‑play scripts
Who it’s for. Developers and researchers building conversational agents that need consistent character voices across Russian, Spanish, English, and Portuguese. The model is suitable for applications that can allocate sufficient GPU memory for a 30.7B parameter weight set.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 32.7 GB | Too big | Get file → | |
| IQ1_S | 7.2 GB | 39.9 GB | Too big | Get file → | |
| IQ1_M | 7.7 GB | 40.4 GB | Too big | Get file → | |
| IQ2_XXS | 8.7 GB | 41.4 GB | Too big | Get file → | |
| IQ2_XS | 9.5 GB | 42.2 GB | Too big | Get file → | |
| IQ2_S | 10.2 GB | 42.9 GB | Too big | Get file → | |
| IQ2_M | 10.9 GB | 43.6 GB | Too big | Get file → | |
| Q2_K_S | 11.0 GB | 43.7 GB | Too big | Get file → | |
| Q2_K | 11.9 GB | 44.6 GB | Too big | Get file → | |
| IQ3_XXS | 12.1 GB | 44.8 GB | Too big | Get file → | |
| IQ3_XS | 13.1 GB | 45.8 GB | Too big | Get file → | |
| IQ3_S | 13.8 GB | 46.5 GB | Too big | Get file → | |
| Q3_K_S | 13.8 GB | 46.5 GB | Too big | Get file → | |
| IQ3_M | 14.4 GB | 47.1 GB | Too big | Get file → | |
| Q3_K_M | 15.3 GB | 48.0 GB | Too big | Get file → | |
| Q3_K_L | 16.6 GB | 49.3 GB | Too big | Get file → | |
| IQ4_XS | 16.7 GB | 49.4 GB | Too big | Get file → | |
| Q4_0 | 17.7 GB | 50.4 GB | Too big | Get file → | |
| Q4_K_S | 17.8 GB | 50.5 GB | Too big | Get file → | |
| Q4_K_M | 18.7 GB | 51.4 GB | Too big | Get file → | |
| Q4_1 | 19.5 GB | 52.2 GB | Too big | Get file → | |
| Q5_K_S | 21.3 GB | 54.0 GB | Too big | Get file → | |
| Q5_K_M | 21.8 GB | 54.6 GB | Too big | Get file → | |
| Q6_K | 25.2 GB | 57.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (7.16 GB) or IQ1_M (7.73 GB). For 12 GB VRAM, IQ2_XS (9.53 GB) or IQ2_S (10.16 GB) are suitable. For 16 GB VRAM, Q4_K_S (17.76 GB) or Q4_K_M (18.69 GB) provide a balance of size and performance. Memory estimates are approximate.
What GPU do you need for Crystal 31B RL?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q3_K_M (15.3 GB file, about 48.0 GB in use).
Which Crystal 31B RL quant should you choose?
Q4_K_M is the usual starting point for Crystal 31B RL: it balances file size and quality well. Here it is a 18.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Crystal 31B RL
How much VRAM does Crystal 31B RL need?
About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Crystal 31B RL on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Crystal 31B RL GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 7.2 GB, IQ1_M is 7.7 GB, IQ2_XXS is 8.7 GB, IQ2_XS is 9.5 GB, IQ2_S is 10.2 GB and 18 more.
What context length does Crystal 31B RL support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download Crystal 31B RL GGUF?
The files are on Hugging Face in the mradermacher/Crystal-31B-RL-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 Crystal 31B RL 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.
Can I run Crystal 31B RL on 8 GB VRAM?
Use the IQ1_S or IQ1_M quantized files; they fit within 8 GB VRAM with an estimated 39.9–40.4 GB memory usage at 8k context.
Does the model support vision?
No, Crystal 31B RL is a text‑only model; vision support is not included.
What license applies to this model?
The model is released under the apache‑2.0 license.