GR

Granite 20b Code Instruct 8k

GraniteGGUF by mradermacherUpdated 2024-09-03
Download on Hugging Face
Parameters20B
Context8K
Layers52
Architecturestarcoder
Smallest quant7.9 GB
Quick answer

Granite 20b Code Instruct 8k needs about 13.5 GB of memory at Q4_K_M (a 12.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 7.9 GB (Q2_K) to 21.5 GB (Q8_0).

Granite 20b Code Instruct 8k – a 20B parameter code‑focused model

Granite 20b Code Instruct 8k is a 20B parameter model fine‑tuned from Granite‑20B‑Code‑Base‑8K on permissively licensed instruction data. It is designed to follow coding instructions and support logical reasoning and problem solving.

Good at

  • Coding instruction following
  • Logical reasoning in code
  • Problem solving in programming

Limits

  • No vision support
  • Designed for coding tasks only
  • Not recommended for new projects

Best for

  • Building coding assistants
  • Generating code snippets
  • Answering code‑related queries

Who it’s for. Developers and researchers needing a code‑centric LLM for historical or scientific purposes. The model is available for use under the Apache 2.0 license but is not recommended for new projects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.9 GB 8.6 GB
Too big Get file →
IQ3_XS8.7 GB 9.4 GB
Too big Get file →
IQ3_S8.9 GB 9.7 GB
Too big Get file →
Q3_K_S8.9 GB 9.7 GB
Too big Get file →
IQ3_M9.6 GB 10.3 GB
Too big Get file →
Q3_K_M10.6 GB 11.3 GB
Too big Get file →
IQ4_XS11.1 GB 11.8 GB
Too big Get file →
Q4_K_S11.7 GB 12.4 GB
Too big Get file →
Q3_K_L11.7 GB 12.5 GB
Too big Get file →
Q4_K_M12.8 GB 13.5 GB
Too big Get file →
Q5_K_S14.0 GB 14.7 GB
Too big Get file →
Q5_K_M14.8 GB 15.5 GB
Too big Get file →
Q6_K16.6 GB 17.4 GB
Too big Get file →
Q8_021.5 GB 22.2 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 7.93 GB, estimated memory 8.6 GB). For 12 GB VRAM, Q4_K_S (file size 11.67 GB, estimated memory 12.4 GB) is a good balance. For 16 GB VRAM, Q4_K_M (file size 12.82 GB, estimated memory 13.5 GB) provides higher quality.

What GPU do you need for Granite 20b Code Instruct 8k?

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: the best quant that fits is IQ4_XS (11.1 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (14.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (21.5 GB file, about 22.2 GB in use).

Which Granite 20b Code Instruct 8k quant should you choose?

Q4_K_M is the usual starting point for Granite 20b Code Instruct 8k: it balances file size and quality well. Here it is a 12.8 GB file.

The Q8_0 file is 21.5 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 7.9 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

Architecturestarcoder
Parameters20B
Layers52
Trained context8,192 tokens
KV cache (fp16)26 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)2,089
Last updated2024-09-03

Frequently asked questions about Granite 20b Code Instruct 8k

How much VRAM does Granite 20b Code Instruct 8k need?

About 13.5 GB at Q4_K_M with an 8K context window. That is the 12.8 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 20b Code Instruct 8k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Granite 20b Code Instruct 8k GGUF?

It depends on the quant: Q2_K is 7.9 GB, IQ3_XS is 8.7 GB, IQ3_S is 8.9 GB, Q3_K_S is 8.9 GB, IQ3_M is 9.6 GB, Q3_K_M is 10.6 GB and 8 more.

What context length does Granite 20b Code Instruct 8k support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download Granite 20b Code Instruct 8k GGUF?

The files are on Hugging Face in the mradermacher/granite-20b-code-instruct-8k-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 20b Code Instruct 8k 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 20b Code Instruct 8k on 8 GB VRAM?

Yes, the Q2_K quant uses about 8.6 GB of VRAM at 8k context, which fits an 8 GB GPU with some headroom.

Does this model support vision tasks?

No, the model is designed for coding and instruction following only.

Is it suitable for new projects?

The model is not recommended for new projects; newer Granite releases are advised.

Other GGUFs of granite-20b-code-instruct-8k

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other medium models

All medium models →