Gemma 4 19B needs about 20.8 GB of memory at Q4_K_M (a 12.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 16.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma 4 19B – 30% MoE pruned, 18.4B parameters
Gemma 4 19B is a 30% expert‑pruned variant of google/gemma‑4‑26b‑a4b‑it using Cerebras REAP. The model keeps 8 experts per token while reducing disk and memory footprint by ~31%. It supports reasoning and tools.
Good at
- Reasoning
- Tool usage
- Large context (262144 tokens)
Limits
- No vision support
- License: gemma
- Requires 8‑k context for memory estimates
Best for
- Chatbots needing large context
- Code generation
- Long‑form reasoning
Who it’s for. Developers building LLM applications that need a balance between performance and resource usage. The model is suitable for users with moderate GPU memory who can benefit from a pruned MoE architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 8.6 GB | Too big | Get file → | |
| IQ1_S | 6.1 GB | 14.7 GB | Too big | Get file → | |
| IQ1_M | 6.4 GB | 14.9 GB | Too big | Get file → | |
| IQ2_XXS | 6.8 GB | 15.4 GB | Too big | Get file → | |
| IQ2_XS | 7.2 GB | 15.8 GB | Too big | Get file → | |
| IQ2_S | 7.3 GB | 15.8 GB | Too big | Get file → | |
| IQ2_M | 7.6 GB | 16.2 GB | Too big | Get file → | |
| Q2_K | 7.8 GB | 16.4 GB | Too big | Get file → | |
| Q2_K_S | 7.8 GB | 16.4 GB | Too big | Get file → | |
| IQ3_XXS | 8.3 GB | 16.9 GB | Too big | Get file → | |
| IQ3_XS | 8.6 GB | 17.1 GB | Too big | Get file → | |
| IQ3_S | 9.0 GB | 17.5 GB | Too big | Get file → | |
| Q3_K_S | 9.0 GB | 17.5 GB | Too big | Get file → | |
| IQ3_M | 9.1 GB | 17.7 GB | Too big | Get file → | |
| Q3_K_M | 9.8 GB | 18.3 GB | Too big | Get file → | |
| Q3_K_L | 10.2 GB | 18.7 GB | Too big | Get file → | |
| IQ4_XS | 10.2 GB | 18.8 GB | Too big | Get file → | |
| IQ4_NL | 10.6 GB | 19.2 GB | Too big | Get file → | |
| Q4_0 | 10.6 GB | 19.2 GB | Too big | Get file → | |
| Q4_K_S | 11.3 GB | 19.9 GB | Too big | Get file → | |
| Q4_1 | 11.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_M | 12.3 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_S | 13.2 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 14.0 GB | 22.5 GB | Too big | Get file → | |
| Q6_K | 16.5 GB | 25.1 GB | Too big | Get file → |
For 8‑GB VRAM use IQ1_S (6.12 GB, 14.7 GB memory at 8k context). For 12‑GB VRAM use Q4_K_M (12.29 GB, 20.8 GB memory). For 16‑GB VRAM use Q5_K_M (13.99 GB, 22.5 GB memory). Estimates are approximate.
What GPU do you need for Gemma 4 19B?
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: the best quant that fits is the main file (0.0 GB file, about 8.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_S (7.3 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (14.0 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (16.5 GB file, about 25.1 GB in use).
Which Gemma 4 19B quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 19B: it balances file size and quality well. Here it is a 12.3 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 Gemma 4 19B
How much VRAM does Gemma 4 19B need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 12.3 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 Gemma 4 19B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 19B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 6.1 GB, IQ1_M is 6.4 GB, IQ2_XXS is 6.8 GB, IQ2_XS is 7.2 GB, IQ2_S is 7.3 GB and 19 more.
What context length does Gemma 4 19B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Gemma 4 19B GGUF?
The files are on Hugging Face in the mradermacher/Gemma-4-19B-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 Gemma 4 19B use?
Hugging Face lists the license as gemma. 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 Gemma 4 19B on an RTX 3090 with 24 GB VRAM?
Yes, the Q6_K quant (16.52 GB, 25.1 GB memory) fits within 24 GB VRAM when using 8k context.
Does this model support vision tasks?
No, Gemma 4 19B is a text‑only model; vision files are not provided.
What context length does it support?
The model was trained with 262144 tokens and can operate with that context length.