LL

h2oai h2ogpt 16k codellama 13b instruct

LlamaGGUF by RichardErkhovUpdated 2024-07-23
Download on Hugging Face
Parameters13B
Context16K
Layers—
Architecturellama
Smallest quant0.0 GB
Quick answer

h2oai h2ogpt 16k codellama 13b instruct needs about 2.4 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.0 GB (Q5_1) to 7.4 GB (Q4_0).

13B Llama-based coding model with 16k context

h2oai h2ogpt 16k codellama 13b instruct is a 13B parameter Llama model fine‑tuned for code generation. It supports up to 16384 tokens of context and is available in multiple GGUF quantizations.

Good at

  • Code generation
  • Programming assistance
  • Language‑specific syntax support

Limits

  • No vision capabilities
  • No license information provided
  • Large memory requirement for higher quants

Best for

  • Writing code snippets
  • Debugging assistance
  • Generating documentation

Who it’s for. Developers and programmers who need a lightweight code assistant. The model is suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_10.0 GB 0.5 GB
Fits Get file →
Q6_K0.0 GB 0.5 GB
Fits Get file →
Q5_K0.0 GB 0.5 GB
Fits Get file →
Q8_00.0 GB 0.5 GB
Fits Get file →
Q5_K_M0.0 GB 0.5 GB
Fits Get file →
Q5_K_S0.0 GB 0.5 GB
Fits Get file →
Q5_00.8 GB 1.3 GB
Fits Get file →
Q4_K_M1.7 GB 2.4 GB
Fits Get file →
Q4_12.0 GB 2.7 GB
Fits Get file →
Q4_K_S2.5 GB 3.2 GB
Fits Get file →
Q4_K2.7 GB 3.5 GB
Fits Get file →
IQ4_XS2.8 GB 3.6 GB
Fits Get file →
Q3_K_S2.9 GB 3.8 GB
Fits Get file →
IQ4_NL3.3 GB 4.2 GB
Fits Get file →
Q3_K4.6 GB 5.6 GB
Fits Get file →
Q2_K4.9 GB 5.9 GB
Fits Get file →
IQ3_XS5.4 GB 6.5 GB
Fits Get file →
IQ3_S5.7 GB 6.8 GB
Fits Get file →
IQ3_M6.0 GB 7.2 GB
Tight Get file →
Q3_K_M6.3 GB 7.6 GB
Tight Get file →
Q3_K_L6.9 GB 8.3 GB
Too big Get file →
Q4_07.4 GB 8.7 GB
Too big Get file →

For 8 GB VRAM, use Q5_1, Q6_K, Q5_K, Q8_0 or Q5_K_M – all estimate 0.5 GB memory at 8 k context. For 16 GB VRAM, Q4_K_M (2.4 GB) or Q4_1 (2.7 GB) are good choices. Larger quants like Q4_K (3.5 GB) or Q3_K (5.6 GB) require more memory.

What GPU do you need for h2oai h2ogpt 16k codellama 13b instruct?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q3_K_S (2.9 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q2_K (4.9 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.3 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_0 (7.4 GB file, about 8.7 GB in use).

Which h2oai h2ogpt 16k codellama 13b instruct quant should you choose?

Q4_K_M is the usual starting point for h2oai h2ogpt 16k codellama 13b instruct: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 0.0 GB, about 0.0 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 Q5_1 at 0.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Trained context16,384 tokens

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)1,247
Last updated2024-07-23

Frequently asked questions about h2oai h2ogpt 16k codellama 13b instruct

How much VRAM does h2oai h2ogpt 16k codellama 13b instruct need?

About 2.4 GB at Q4_K_M with an 8K context window. That is the 1.7 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 h2oai h2ogpt 16k codellama 13b instruct on an 8 GB GPU?

Yes, with Q3_K_M: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of h2oai h2ogpt 16k codellama 13b instruct GGUF?

It depends on the quant: Q5_1 is 0.0 GB, Q6_K is 0.0 GB, Q5_K is 0.0 GB, Q8_0 is 0.0 GB, Q5_K_M is 0.0 GB, Q5_K_S is 0.0 GB and 16 more.

What context length does h2oai h2ogpt 16k codellama 13b instruct support?

The GGUF header lists a trained context length of 16,384 tokens (16K).

Where can I download h2oai h2ogpt 16k codellama 13b instruct GGUF?

The files are on Hugging Face in the RichardErkhov/h2oai_-_h2ogpt-16k-codellama-13b-instruct-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 this model on 8 GB VRAM?

Yes, using Q5_1, Q6_K, Q5_K, Q8_0 or Q5_K_M which estimate 0.5 GB memory at 8 k context.

Does the model support image input?

No, the model has no vision capabilities.

What is the context length?

The model supports 16384 tokens of context.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other medium models

All medium models →