GR

granite-7b-lab

GraniteGGUF by RichardErkhovUpdated 2024-06-22
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

granite-7b-lab needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 2.5 GB (Q2_K) to 7.2 GB (Q8_0).

Granite-7b-lab: 6.74B parameter Llama-based instruction model

Granite-7b-lab is a 6.74B parameter Llama model fine‑tuned with IBM Research’s LAB methodology. It uses synthetic data and a taxonomy‑driven approach to add knowledge without catastrophic forgetting. The model supports a 4096 token context window.

Good at

  • Instruction following
  • Synthetic data generation
  • Knowledge expansion

Limits

  • No vision support
  • License not specified
  • No mixture of experts

Best for

  • Chatbot development
  • Instruction‑driven applications
  • Knowledge‑heavy tasks

Who it’s for. Developers building chat or instruction‑based LLM applications who need a 6.74B model with a 4096 token context. The model is suitable for environments where the 8‑k context memory estimate is acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 5.2 GB
Fits Get file →
IQ3_XS2.8 GB 5.4 GB
Fits Get file →
IQ3_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
IQ3_M3.1 GB 5.8 GB
Fits Get file →
Q3_K3.3 GB 5.9 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
IQ4_XS3.6 GB 6.3 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
IQ4_NL3.8 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K4.1 GB 6.7 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q4_14.2 GB 6.9 GB
Fits Get file →
Q5_04.7 GB 7.3 GB
Tight Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K4.8 GB 7.4 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q5_15.1 GB 7.7 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (file size 2.53 GB, memory 7.3 GB) or IQ3_XS (2.8 GB, 7.6 GB). For 12‑GB VRAM, Q6_K (5.53 GB, 10.3 GB) or Q8_0 (7.16 GB, 12 GB) provide higher quality. Memory estimates are approximate.

What GPU do you need for granite-7b-lab?

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: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which granite-7b-lab quant should you choose?

Q4_K_M is the usual starting point for granite-7b-lab: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.5 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
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byRichardErkhov
FamilyGranite
Downloads (HF)901
Last updated2024-06-22

Frequently asked questions about granite-7b-lab

How much VRAM does granite-7b-lab need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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-7b-lab on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite-7b-lab GGUF?

It depends on the quant: Q2_K is 2.5 GB, IQ3_XS is 2.8 GB, IQ3_S is 2.9 GB, Q3_K_S is 2.9 GB, IQ3_M is 3.1 GB, Q3_K is 3.3 GB and 16 more.

What context length does granite-7b-lab support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download granite-7b-lab GGUF?

The files are on Hugging Face in the RichardErkhov/instructlab_-_granite-7b-lab-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Granite-7b-lab on 8 GB VRAM?

Yes, using Q2_K or IQ3_XS quantizations, which require about 7.3–7.6 GB of VRAM at 8‑k context.

What is the context length of Granite-7b-lab?

The model supports a 4096 token context window.

Does Granite-7b-lab support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Granite models

All Granite →

Other small models

All small models →