Glistening Gem 31B v2.1 needs about 52.3 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 28 quants, from 0.0 GB to 61.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
31‑B Gemma‑4 model with vision and creative text output
Glistening Gem 31B v2.1 is a 31 B parameter Gemma‑4 merge that supports text, image, and audio input. It is released under Apache 2.0 and is optimized for creative writing. The model retains the original Gemma‑4 architecture while adding multimodal capabilities.
Good at
- Creative prose generation
- Multimodal text and image tasks
- Large context handling
Limits
- Rare word‑fusion artifacts
- Not suited for strict reasoning tasks
- Requires 8 k context for memory estimates
Best for
- Writing fiction or poetry
- Generating image captions
- Creative brainstorming
Who it’s for. Developers and content creators who need a large‑context, multimodal model for creative tasks. The model is suitable for local deployment with llama.cpp or compatible tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 32.7 GB | Too big | Get file → | |
| IQ2_XXS | 10.8 GB | 43.5 GB | Too big | Get file → | |
| IQ2_XS | 11.5 GB | 44.2 GB | Too big | Get file → | |
| IQ2_S | 12.1 GB | 44.8 GB | Too big | Get file → | |
| Q2_K | 12.6 GB | 45.3 GB | Too big | Get file → | |
| IQ2_M | 12.6 GB | 45.4 GB | Too big | Get file → | |
| Q2_K_L | 13.0 GB | 45.7 GB | Too big | Get file → | |
| IQ3_XXS | 13.0 GB | 45.7 GB | Too big | Get file → | |
| IQ3_XS | 13.8 GB | 46.6 GB | Too big | Get file → | |
| Q3_K_S | 14.3 GB | 47.0 GB | Too big | Get file → | |
| IQ3_M | 15.1 GB | 47.8 GB | Too big | Get file → | |
| Q3_K_M | 15.9 GB | 48.6 GB | Too big | Get file → | |
| Q3_K_L | 16.8 GB | 49.5 GB | Too big | Get file → | |
| Q3_K_XL | 17.2 GB | 49.9 GB | Too big | Get file → | |
| IQ4_XS | 17.2 GB | 49.9 GB | Too big | Get file → | |
| IQ4_NL | 18.0 GB | 50.7 GB | Too big | Get file → | |
| Q4_0 | 18.1 GB | 50.8 GB | Too big | Get file → | |
| Q4_K_S | 18.2 GB | 50.9 GB | Too big | Get file → | |
| Q4_K_M | 19.6 GB | 52.3 GB | Too big | Get file → | |
| Q4_1 | 19.8 GB | 52.5 GB | Too big | Get file → | |
| Q4_K_L | 19.9 GB | 52.7 GB | Too big | Get file → | |
| Q5_K_S | 21.5 GB | 54.2 GB | Too big | Get file → | |
| Q5_K_M | 22.6 GB | 55.3 GB | Too big | Get file → | |
| Q5_K_L | 23.0 GB | 55.7 GB | Too big | Get file → | |
| Q6_K | 26.7 GB | 59.4 GB | Too big | Get file → | |
| Q6_K_L | 27.1 GB | 59.8 GB | Too big | Get file → | |
| Q8_0 | 32.6 GB | 65.3 GB | Too big | Get file → | |
| BF16 | 61.4 GB (2 parts) | 94.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (19.6 GB) or Q4_K_S (18.2 GB). With 16 GB VRAM, Q5_K_M (22.6 GB) or Q6_K (26.7 GB) provide a balance of size and performance. For larger budgets, Q8_0 (32.6 GB) or BF16 (61.4 GB) offer higher fidelity.
What GPU do you need for Glistening Gem 31B v2.1?
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 IQ3_M (15.1 GB file, about 47.8 GB in use).
Which Glistening Gem 31B v2.1 quant should you choose?
Q4_K_M is the usual starting point for Glistening Gem 31B v2.1: it balances file size and quality well. Here it is a 19.6 GB file.
The Q8_0 file is 32.6 GB, about 1.7 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 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 Glistening Gem 31B v2.1
How much VRAM does Glistening Gem 31B v2.1 need?
About 52.3 GB at Q4_K_M with an 8K context window. That is the 19.6 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 Glistening Gem 31B v2.1 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 Glistening Gem 31B v2.1 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 10.8 GB, IQ2_XS is 11.5 GB, IQ2_S is 12.1 GB, Q2_K is 12.6 GB, IQ2_M is 12.6 GB and 22 more.
What context length does Glistening Gem 31B v2.1 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 Glistening Gem 31B v2.1 GGUF?
The files are on Hugging Face in the bartowski/sophosympatheia_Glistening-Gem-31B-v2.1-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 Glistening Gem 31B v2.1 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 Glistening Gem 31B v2.1 on 8 GB VRAM?
Use the Q4_K_M or Q4_K_S quantization; each requires about 50 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does the model support image input?
Yes, it supports image and audio input via the included mmproj projector files.
What sampler settings are recommended?
Start with Temp 0.8, Min-P, and Adaptive-P as suggested in the repository for creative tasks.