GO

Goose 7.2B G1j 20260914

GooseGGUF by mradermacherUpdated 2026-09-15
Download on Hugging Face
Parameters7.2B
Context1024K
Layers32
Architecturerwkv7
Smallest quant2.9 GB
Quick answer

Goose 7.2B G1j 20260914 needs about 5.6 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.9 GB (Q2_K) to 14.5 GB (F16).

Goose 7.2B G1j – RWKV7 model with reasoning and tool use

Goose 7.2B G1j is a 7.2‑billion parameter RWKV7 model. It supports reasoning and tool usage. The model is released under apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Reasoning
  • Tool use
  • Long‑context handling

Limits

  • No vision support
  • Large VRAM required for higher quants
  • Not a full post‑trained model

Best for

  • Chatbot with tool integration
  • Long‑form reasoning tasks
  • Custom tool pipelines

Who it’s for. Developers building LLM‑powered assistants that need reasoning and tool invocation. The model is suitable for users who can manage the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.9 GB 3.8 GB
Fits Get file →
Q3_K_L3.6 GB 4.6 GB
Fits Get file →
Q3_K_M3.6 GB 4.6 GB
Fits Get file →
Q3_K_S3.6 GB 4.6 GB
Fits Get file →
IQ4_XS4.3 GB 5.3 GB
Fits Get file →
Q4_K_M4.5 GB 5.6 GB
Fits Get file →
Q4_K_S4.5 GB 5.6 GB
Fits Get file →
Q5_K_M5.3 GB 6.5 GB
Fits Get file →
Q5_K_S5.3 GB 6.5 GB
Fits Get file →
Q6_K6.2 GB 7.5 GB
Tight Get file →
Q8_07.9 GB 9.4 GB
Too big Get file →
F1614.5 GB 16.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (est. 5.6 GB) or Q3_K_M (est. 4.6 GB). For 12 GB VRAM, Q5_K_M (est. 6.5 GB) or Q6_K (est. 7.5 GB) are suitable. Higher‑precision quants like F16 require 16.7 GB and are not recommended for limited VRAM.

What GPU do you need for Goose 7.2B G1j 20260914?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q2_K (2.9 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.5 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 9.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 9.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.7 GB in use).

Which Goose 7.2B G1j 20260914 quant should you choose?

Q4_K_M is the usual starting point for Goose 7.2B G1j 20260914: it balances file size and quality well. Here it is a 4.5 GB file.

The Q8_0 file is 7.9 GB, about 1.8 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 2.9 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

Architecturerwkv7
Parameters7.2B
Layers32
Trained context1,048,576 tokens

Source

Quantized bymradermacher
FamilyGoose
Licenseapache-2.0
Downloads (HF)592
Last updated2026-09-15

Frequently asked questions about Goose 7.2B G1j 20260914

How much VRAM does Goose 7.2B G1j 20260914 need?

About 5.6 GB at Q4_K_M with an 8K context window. That is the 4.5 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 Goose 7.2B G1j 20260914 on an 8 GB GPU?

Yes, with Q6_K: the 6.2 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Goose 7.2B G1j 20260914 GGUF?

It depends on the quant: Q2_K is 2.9 GB, Q3_K_L is 3.6 GB, Q3_K_M is 3.6 GB, Q3_K_S is 3.6 GB, IQ4_XS is 4.3 GB, Q4_K_M is 4.5 GB and 6 more.

What context length does Goose 7.2B G1j 20260914 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download Goose 7.2B G1j 20260914 GGUF?

The files are on Hugging Face in the mradermacher/Goose-7.2B-G1j-20260914-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 Goose 7.2B G1j 20260914 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 Goose 7.2B G1j on 8 GB VRAM?

Yes, using Q4_K_M or Q3_K_M quantizations, which estimate 5.6 GB or 4.6 GB memory at 8 k context.

Does this model support vision?

No, Goose 7.2B G1j does not include vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Goose-7.2B-G1j-20260914

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Goose models

All Goose →

Other small models

All small models →