TE

test gguf models

TestGGUF by ngxsonUpdated 2024-07-10
Download on Hugging Face
Parameters2B
Context32K
Layers24
Architectureqwen2
Smallest quant0.0 GB
Quick answer

test gguf models needs about 3.3 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.0 GB to 4.7 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Test GGUF Models – 2B Qwen2 architecture

Test GGUF Models is a 2B parameter Qwen2 model released under the MIT license. It supports a 32768 token context window and is available in several quantized formats. The model is language-agnostic with no detected special abilities.

Good at

  • Large context handling
  • Low memory Q5_1 quant
  • Sharded Q4_K_M for 8‑k context

Limits

  • No vision support
  • No mixture of experts
  • License is MIT

Best for

  • Chatbots needing long context
  • Lightweight inference on 8‑GB VRAM
  • Batch processing with sharded models

Who it’s for. Developers building LLM applications that require a 32768 token context window and can work with a 2B parameter model. The MIT license allows free use in commercial projects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.1 GB
Fits Get file →
—0.0 GB 2.1 GB
Fits Get file →
Q5_10.0 GB 2.1 GB
Fits Get file →
—0.0 GB 2.1 GB
Fits Get file →
—0.1 GB 2.2 GB
Fits Get file →
Q4_K_M1.2 GB (5 parts) 3.3 GB
Fits Get file →
Q4_K_S4.7 GB (16 parts) 6.8 GB
Fits Get file →

For 8‑GB VRAM, use the Q5_1 quant (0.03 GB file, 2.1 GB memory at 8‑k context). If more memory is available, the Q4_K_M sharded version (1.22 GB file, 3.3 GB memory) offers better precision. The Q4_K_S sharded file (4.69 GB, 6.8 GB memory) is suitable for larger GPU budgets.

What GPU do you need for test gguf models?

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: the best quant that fits is Q4_K_M (1.2 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (1.2 GB file, about 3.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (4.7 GB file, about 6.8 GB in use).

Which test gguf models quant should you choose?

Q4_K_M is the usual starting point for test gguf models: it balances file size and quality well. Here it is a 1.2 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

Architectureqwen2
Parameters2B
Layers24
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byngxson
FamilyTest
Licensemit
Downloads (HF)2,054
Last updated2024-07-10

Frequently asked questions about test gguf models

How much VRAM does test gguf models need?

About 3.3 GB at Q4_K_M with an 8K context window. That is the 1.2 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 test gguf models on an 8 GB GPU?

Yes, with Q4_K_S: the 4.7 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of test gguf models GGUF?

It depends on the quant: file is 0.0 GB, file is 0.0 GB, Q5_1 is 0.0 GB, file is 0.0 GB, file is 0.1 GB, Q4_K_M is 1.2 GB and 1 more.

What context length does test gguf models support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download test gguf models GGUF?

The files are on Hugging Face in the ngxson/test_gguf_models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does test gguf models use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, the Q5_1 quant uses approximately 2.1 GB memory at 8‑k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

No, the model has no vision capabilities.

Is the model licensed for commercial use?

Yes, it is released under the MIT license, which permits commercial use.

Similar models

Browse all →

More from ngxson

All by ngxson →

More Test models

All Test →

Other tiny models

All tiny models →