GR

Granite 3b Code Instruct 128k

GraniteGGUF by RichardErkhovUpdated 2024-08-22
Download on Hugging Face
Parameters3.48B
Context125K
Layers32
Architecturellama
Smallest quant1.3 GB
Quick answer

Granite 3b Code Instruct 128k 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 22 quants, from 1.3 GB (Q2_K) to 3.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Granite 3b Code Instruct 128k – a 3.48B parameter code‑focused LLM

Granite 3b Code Instruct 128k is a 3.48B parameter model trained on large code datasets. It supports up to 128,000 token context and is licensed under apache‑2.0. The model is optimized for code generation and instruction following.

Good at

  • Code generation
  • Instruction following
  • Large context handling

Limits

  • No vision support
  • Limited to text generation
  • Requires 8,000 token context for memory estimates

Best for

  • Writing code snippets
  • Automating code documentation
  • Debugging assistance

Who it’s for. Developers and researchers needing a lightweight code model with extended context. The model is suitable for local inference on machines with moderate VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.3 GB 4.5 GB
Fits Get file →
IQ3_XS1.5 GB 4.7 GB
Fits Get file →
IQ3_S1.6 GB 4.7 GB
Fits Get file →
Q3_K_S1.6 GB 4.7 GB
Fits Get file →
IQ3_M1.6 GB 4.8 GB
Fits Get file →
Q3_K1.7 GB 4.9 GB
Fits Get file →
Q3_K_M1.7 GB 4.9 GB
Fits Get file →
Q3_K_L1.9 GB 5.1 GB
Fits Get file →
IQ4_XS1.9 GB 5.1 GB
Fits Get file →
Q4_02.0 GB 5.2 GB
Fits Get file →
IQ4_NL2.0 GB 5.2 GB
Fits Get file →
Q4_K_S2.0 GB 5.2 GB
Fits Get file →
Q4_K2.1 GB 5.3 GB
Fits Get file →
Q4_K_M2.1 GB 5.3 GB
Fits Get file →
Q4_12.2 GB 5.4 GB
Fits Get file →
Q5_02.4 GB 5.6 GB
Fits Get file →
Q5_K_S2.4 GB 5.6 GB
Fits Get file →
Q5_K2.5 GB 5.7 GB
Fits Get file →
Q5_K_M2.5 GB 5.7 GB
Fits Get file →
Q5_12.6 GB 5.8 GB
Fits Get file →
Q6_K2.9 GB 6.0 GB
Fits Get file →
Q8_03.7 GB 6.9 GB
Fits Get file →

For 8 GB VRAM use Q4_0 (file size 2 GB, ~5.2 GB memory). For 12 GB VRAM use Q5_0 (file size 2.42 GB, ~5.6 GB memory). For 16 GB VRAM use Q6_K (file size 2.86 GB, ~6 GB memory). Estimates are approximate.

What GPU do you need for Granite 3b Code Instruct 128k?

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).

Which Granite 3b Code Instruct 128k quant should you choose?

Q4_K_M is the usual starting point for Granite 3b Code Instruct 128k: 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 context128,000 tokens
KV cache (fp16)320 KB per token

Source

Quantized byRichardErkhov
FamilyGranite
Licenseapache-2.0
Downloads (HF)2,904
Last updated2024-08-22

Frequently asked questions about Granite 3b Code Instruct 128k

How much VRAM does Granite 3b Code Instruct 128k 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 Instruct 128k 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 Instruct 128k 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 is 1.7 GB and 16 more.

What context length does Granite 3b Code Instruct 128k support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Granite 3b Code Instruct 128k GGUF?

The files are on Hugging Face in the RichardErkhov/ibm-granite_-_granite-3b-code-instruct-128k-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 Instruct 128k 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 Granite 3b Code Instruct 128k on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 5.2 GB of VRAM at 8,000 token context.

Does this model support image input?

No, it is a text‑only model with 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 RichardErkhov

All by RichardErkhov →

More Granite models

All Granite →

Other tiny models

All tiny models →