GE

gemma 4 A4B 98e v7 coderx it

GemmaGGUF by ManniX-ITAUpdated 2026-09-16
Download on Hugging Face
Parameters19.9B
Context256K
Layers30
Architecturegemma4
Smallest quant8.8 GB
Quick answer

gemma 4 A4B 98e v7 coderx it needs about 21.8 GB of memory at Q4_K_M (a 13.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 8.8 GB (Q2_K) to 39.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma 4 A4B 98e v7 coderx – code‑focused, 19.9B parameter model

Gemma 4 A4B 98e v7 coderx is a 19.9B parameter model with 4B active experts. It is trained on a 262144 token context and supports coding and vision tasks. The model is released under the apache-2.0 license.

Good at

  • High‑accuracy code generation
  • Vision‑enabled multimodal input
  • Large context handling

Limits

  • No support for vision in quantized files without the shared SigLIP tower
  • Requires at least 17.4 GB VRAM for Q2_K at 8 k context
  • Limited to 262144 token context

Best for

  • Developing code assistants
  • Multimodal research prototypes
  • Large‑context document analysis

Who it’s for. Engineers and researchers needing a code‑centric LLM with vision support. The model is suitable for developers building code generation tools and researchers exploring multimodal capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.8 GB 17.4 GB
Too big Get file →
Q3_K_M10.5 GB 19.1 GB
Too big Get file →
Q3_K_L10.9 GB 19.5 GB
Too big Get file →
IQ4_XS11.0 GB 19.6 GB
Too big Get file →
IQ4_NL11.4 GB 20.0 GB
Too big Get file →
Q4_K_S12.2 GB 20.8 GB
Too big Get file →
Q4_K_M13.2 GB 21.8 GB
Too big Get file →
Q4_K_L13.4 GB 22.0 GB
Too big Get file →
Q5_K_M15.1 GB 23.6 GB
Too big Get file →
Q5_K_L15.2 GB 23.8 GB
Too big Get file →
Q6_K17.8 GB 26.4 GB
Too big Get file →
Q6_K_L18.0 GB 26.5 GB
Too big Get file →
Q8_021.2 GB 29.7 GB
Too big Get file →
F1639.8 GB 48.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (8.82 GB file, 17.4 GB memory at 8 k context). For 12 GB VRAM, Q4_K_S (12.21 GB file, 20.8 GB memory). For 20 GB VRAM, Q6_K (17.81 GB file, 26.4 GB memory). The estimates are approximate.

What GPU do you need for gemma 4 A4B 98e v7 coderx it?

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: the best quant that fits is Q5_K_L (15.2 GB file, about 23.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (21.2 GB file, about 29.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (21.2 GB file, about 29.7 GB in use).

Which gemma 4 A4B 98e v7 coderx it quant should you choose?

Q4_K_M is the usual starting point for gemma 4 A4B 98e v7 coderx it: it balances file size and quality well. Here it is a 13.2 GB file.

The Q8_0 file is 21.2 GB, about 1.6 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 Q2_K at 8.8 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

Architecturegemma4
Parameters19.9B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized byManniX-ITA
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,705
Last updated2026-09-16

Frequently asked questions about gemma 4 A4B 98e v7 coderx it

How much VRAM does gemma 4 A4B 98e v7 coderx it need?

About 21.8 GB at Q4_K_M with an 8K context window. That is the 13.2 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 A4B 98e v7 coderx it on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 A4B 98e v7 coderx it GGUF?

It depends on the quant: Q2_K is 8.8 GB, Q3_K_M is 10.5 GB, Q3_K_L is 10.9 GB, IQ4_XS is 11.0 GB, IQ4_NL is 11.4 GB, Q4_K_S is 12.2 GB and 8 more.

What context length does gemma 4 A4B 98e v7 coderx it 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 A4B 98e v7 coderx it GGUF?

The files are on Hugging Face in the ManniX-ITA/gemma-4-A4B-98e-v7-coderx-it-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 A4B 98e v7 coderx it 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 Gemma 4 A4B 98e v7 coderx on 8 GB VRAM?

The smallest quant, Q2_K, requires 17.4 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does the model support vision tasks?

Yes, but only when the shared SigLIP tower is included; the quantized files listed do not contain it.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of gemma-4-A4B-98e-v7-coderx-it

Similar models

Browse all →

More from ManniX-ITA

All by ManniX-ITA →

More Gemma models

All Gemma →

Other medium models

All medium models →