GR

granite-3b-code-glaive-20k

GraniteGGUF by mradermacherUpdated 2024-06-06
Download on Hugging Face
Parameters3.48B
Context2K
Layers32
Architecturellama
Smallest quant1.3 GB
Quick answer

granite-3b-code-glaive-20k needs about 5.3 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.3 GB (Q2_K) to 7.0 GB (F16).

Granite 3B Code model fine‑tuned for coding tasks

Granite‑3B‑Code‑Glaive‑20k is a 3.48 billion parameter llama architecture model. It is fine‑tuned from granite‑3b‑code‑base on a 20k sample subset of glaive‑code‑assistant‑v3. The model is licensed under apache‑2.0.

Good at

  • Coding assistance
  • Code generation
  • Syntax correction

Limits

  • No vision support
  • Context limited to 2048 tokens
  • Requires at least 4.5 GB VRAM for Q2_K

Best for

  • Developers needing lightweight code models
  • Embedded systems with limited VRAM
  • Rapid prototyping of code snippets

Who it’s for. Engineers and hobbyists who need a small, open‑source code model for local inference. The model is suitable for projects that require a lightweight, GPL‑compatible solution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.3 GB 2.5 GB
Fits Get file →
IQ3_XS1.5 GB 2.6 GB
Fits Get file →
IQ3_S1.6 GB 2.7 GB
Fits Get file →
Q3_K_S1.6 GB 2.7 GB
Fits Get file →
IQ3_M1.6 GB 2.8 GB
Fits Get file →
Q3_K_M1.7 GB 2.9 GB
Fits Get file →
Q3_K_L1.9 GB 3.0 GB
Fits Get file →
IQ4_XS1.9 GB 3.1 GB
Fits Get file →
Q4_K_S2.0 GB 3.2 GB
Fits Get file →
Q4_K_M2.1 GB 3.3 GB
Fits Get file →
Q5_K_S2.4 GB 3.6 GB
Fits Get file →
Q5_K_M2.5 GB 3.7 GB
Fits Get file →
Q6_K2.9 GB 4.0 GB
Fits Get file →
Q8_03.7 GB 4.9 GB
Fits Get file →
F167.0 GB 8.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.13 GB file, ~5.3 GB memory). If 4 GB VRAM is available, Q2_K (1.34 GB file, ~4.5 GB memory) is the smallest option. For higher quality, consider Q5_K_M (2.49 GB file, ~5.7 GB memory).

What GPU do you need for granite-3b-code-glaive-20k?

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: the best quant that fits is Q6_K (2.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 6.9 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.0 GB file, about 10.2 GB in use).

Which granite-3b-code-glaive-20k quant should you choose?

Q4_K_M is the usual starting point for granite-3b-code-glaive-20k: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.7 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 Q2_K at 1.3 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

Architecturellama
Parameters3.48B
Layers32
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)868
Last updated2024-06-06

Frequently asked questions about granite-3b-code-glaive-20k

How much VRAM does granite-3b-code-glaive-20k need?

About 5.3 GB at Q4_K_M with an 8K context window. That is the 2.1 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 granite-3b-code-glaive-20k on an 8 GB GPU?

Yes, with Q8_0: the 3.7 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite-3b-code-glaive-20k GGUF?

It depends on the quant: Q2_K is 1.3 GB, IQ3_XS is 1.5 GB, IQ3_S is 1.6 GB, Q3_K_S is 1.6 GB, IQ3_M is 1.6 GB, Q3_K_M is 1.7 GB and 9 more.

What context length does granite-3b-code-glaive-20k support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download granite-3b-code-glaive-20k GGUF?

The files are on Hugging Face in the mradermacher/granite-3b-code-glaive-20k-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 granite-3b-code-glaive-20k 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 5.3 GB VRAM at 8k context, which fits within 8 GB.

Does the model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other tiny models

All tiny models →