GL

Glistening Gem 31B v2.0

GlisteningGGUF by bartowskiUpdated 2026-08-15
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Glistening Gem 31B v2.0 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.

Glistening Gem 31B v2.0 – a 31B Gemma‑4 model with creative merge

Glistening Gem 31B v2.0 is a 30.7B parameter Gemma‑4 model released under Apache‑2.0. It merges several prior models to improve stability and creativity. The model supports 262144‑token context and is available in multiple GGUF quantizations.

Good at

  • Creative text generation
  • Large context handling
  • Stable inference

Limits

  • Known lm_head issues may affect output quality
  • No vision support
  • Requires recent llama.cpp release

Best for

  • Long‑form storytelling
  • Complex dialogue simulation
  • Research prototyping

Who it’s for. Developers and researchers needing a large‑parameter Gemma‑4 model for text‑only tasks. The model is suitable for those who can manage the known lm_head issue and have sufficient GPU memory for the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 32.7 GB
Too big Get file →
IQ2_XXS10.8 GB 43.5 GB
Too big Get file →
IQ2_XS11.5 GB 44.2 GB
Too big Get file →
IQ2_S12.1 GB 44.8 GB
Too big Get file →
Q2_K12.6 GB 45.3 GB
Too big Get file →
IQ2_M12.6 GB 45.4 GB
Too big Get file →
Q2_K_L13.0 GB 45.7 GB
Too big Get file →
IQ3_XXS13.0 GB 45.7 GB
Too big Get file →
IQ3_XS13.8 GB 46.6 GB
Too big Get file →
Q3_K_S14.3 GB 47.0 GB
Too big Get file →
IQ3_M15.1 GB 47.8 GB
Too big Get file →
Q3_K_M15.9 GB 48.6 GB
Too big Get file →
Q3_K_L16.8 GB 49.5 GB
Too big Get file →
Q3_K_XL17.2 GB 49.9 GB
Too big Get file →
IQ4_XS17.2 GB 49.9 GB
Too big Get file →
IQ4_NL18.0 GB 50.7 GB
Too big Get file →
Q4_018.1 GB 50.8 GB
Too big Get file →
Q4_K_S18.2 GB 50.9 GB
Too big Get file →
Q4_K_M19.6 GB 52.3 GB
Too big Get file →
Q4_119.8 GB 52.5 GB
Too big Get file →
Q4_K_L19.9 GB 52.7 GB
Too big Get file →
Q5_K_S21.5 GB 54.2 GB
Too big Get file →
Q5_K_M22.6 GB 55.3 GB
Too big Get file →
Q5_K_L23.0 GB 55.7 GB
Too big Get file →
Q6_K26.7 GB 59.4 GB
Too big Get file →
Q6_K_L27.1 GB 59.8 GB
Too big Get file →
Q8_032.6 GB 65.3 GB
Too big Get file →
BF1661.4 GB (2 parts) 94.1 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XXS (10.83 GB file, 43.5 GB memory at 8k context). For 16‑GB VRAM, Q4_K_M (19.60 GB file, 52.3 GB memory) offers a good balance. For 32‑GB VRAM, Q8_0 (32.64 GB file, 65.3 GB memory) provides the highest quality.

What GPU do you need for Glistening Gem 31B v2.0?

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 v2.0 quant should you choose?

Q4_K_M is the usual starting point for Glistening Gem 31B v2.0: 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

Architecturegemma4
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized bybartowski
Licenseapache-2.0
Downloads (HF)2,448
Last updated2026-08-15

Frequently asked questions about Glistening Gem 31B v2.0

How much VRAM does Glistening Gem 31B v2.0 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 v2.0 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 v2.0 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 v2.0 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 v2.0 GGUF?

The files are on Hugging Face in the bartowski/sophosympatheia_Glistening-Gem-31B-v2.0-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 v2.0 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 v2.0 on 8 GB VRAM?

Use the IQ2_XXS quant, which requires 10.83 GB file size and estimates 43.5 GB memory at 8k context. It will need CPU fallback or swap for full inference.

Does this model support vision input?

No, the model only supports text input. Vision tensors are missing in the current weights.

What is the impact of the lm_head issue?

The fine‑tuned lm_head may produce incoherent output. It is recommended to avoid using the original lm_head weights for production.

Other GGUFs of Glistening-Gem-31B-v2.0

Similar models

Browse all →

More from bartowski

All by bartowski →

More Glistening models

All Glistening →

Other medium models

All medium models →