WA

wavecoder-ultra-1.1-6.7b

WavecoderGGUF by bartowskiUpdated 2024-04-26
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

wavecoder-ultra-1.1-6.7b 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 1.5 GB (IQ1_S) to 7.2 GB (Q8_0).

Wavecoder Ultra 6.7B, a coding‑focused LLM

Wavecoder Ultra 6.7B is a 6.74B‑parameter model designed for code generation. It supports a 16384‑token context window and is released under the MIT license. The model is available in multiple GGUF quantizations.

Good at

  • Code generation
  • Syntax‑aware programming tasks
  • Language‑agnostic coding

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No mixture of experts

Best for

  • Developers needing on‑device code assistants
  • Embedded coding tools
  • Educational coding platforms

Who it’s for. Engineers and hobbyists who want a lightweight code model for local inference. The model is suitable for developers building custom coding assistants or educational tools that run on consumer GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 6.3 GB
Fits Get file →
IQ1_M1.7 GB 6.4 GB
Fits Get file →
IQ2_XXS1.9 GB 6.7 GB
Fits Get file →
IQ2_XS2.0 GB 6.8 GB
Fits Get file →
IQ2_S2.2 GB 7.0 GB
Fits Get file →
IQ2_M2.4 GB 7.2 GB
Fits Get file →
Q2_K2.5 GB 7.3 GB
Tight Get file →
IQ3_XXS2.6 GB 7.4 GB
Tight Get file →
IQ3_XS2.8 GB 7.6 GB
Tight Get file →
IQ3_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
IQ3_M3.1 GB 7.9 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
IQ4_XS3.6 GB 8.4 GB
Too big Get file →
IQ4_NL3.8 GB 8.6 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS (2.04 GB) or Q4_K_S (3.86 GB) for a balance of speed and quality. With 12 GB VRAM, Q5_K_M (4.78 GB) or Q6_K (5.53 GB) provide higher fidelity. For 16 GB VRAM, Q8_0 (7.16 GB) offers the best quality within memory limits.

What GPU do you need for wavecoder-ultra-1.1-6.7b?

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 wavecoder-ultra-1.1-6.7b quant should you choose?

Q4_K_M is the usual starting point for wavecoder-ultra-1.1-6.7b: 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 IQ1_S at 1.5 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 context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bybartowski
FamilyWavecoder
Licensemit
Downloads (HF)921
Last updated2024-04-26

Frequently asked questions about wavecoder-ultra-1.1-6.7b

How much VRAM does wavecoder-ultra-1.1-6.7b 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 wavecoder-ultra-1.1-6.7b 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 wavecoder-ultra-1.1-6.7b GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB, IQ2_M is 2.4 GB and 16 more.

What context length does wavecoder-ultra-1.1-6.7b support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download wavecoder-ultra-1.1-6.7b GGUF?

The files are on Hugging Face in the bartowski/wavecoder-ultra-1.1-6.7b-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 wavecoder-ultra-1.1-6.7b use?

Hugging Face lists the license as mit. 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 Wavecoder Ultra on 8 GB VRAM?

Yes, use a quant file around 2–4 GB, such as IQ2_XS or Q4_K_S, to fit within 8 GB VRAM.

Does the model support GPU acceleration?

Yes, it works with llama.cpp using cuBLAS or rocBLAS for Nvidia or AMD GPUs.

Is there a vision capability?

No, the model only handles text and code.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Wavecoder models

All Wavecoder →

Other small models

All small models →