LL

MultiPL-T-CodeLlama_34b

LlamaGGUF by mradermacherUpdated 2024-06-25
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant12.5 GB
Quick answer

MultiPL-T-CodeLlama_34b needs about 22.3 GB of memory at Q4_K_M (a 20.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 12.5 GB (Q2_K) to 35.9 GB (Q8_0).

MultiPL-T CodeLlama‑34b fine‑tuned for coding

MultiPL‑T CodeLlama‑34b is a 33.7 billion‑parameter Llama model fine‑tuned on MultiPL‑T data. It supports 16384 context tokens and is released under the openrail license. The model is available in multiple GGUF quantizations.

Good at

  • coding tasks
  • multi‑language code generation
  • context‑aware code completion

Limits

  • no vision support
  • requires 8 k context for memory estimates
  • openrail license restrictions

Best for

  • code autocompletion in IDEs
  • generating boilerplate code
  • educational coding assistants

Who it’s for. Developers and researchers needing a large‑scale code generation model. The model is suitable for local deployment via llama.cpp and for integration into coding tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.5 GB 14.6 GB
Too big Get file →
IQ3_XS13.9 GB 16.0 GB
Too big Get file →
Q3_K_S14.6 GB 16.7 GB
Too big Get file →
IQ3_S14.7 GB 16.8 GB
Too big Get file →
IQ3_M15.2 GB 17.3 GB
Too big Get file →
Q3_K_M16.3 GB 18.4 GB
Too big Get file →
Q3_K_L17.8 GB 19.9 GB
Too big Get file →
IQ4_XS18.2 GB 20.3 GB
Too big Get file →
Q4_K_S19.2 GB 21.3 GB
Too big Get file →
Q4_K_M20.2 GB 22.3 GB
Too big Get file →
Q5_K_S23.2 GB 25.3 GB
Too big Get file →
Q5_K_M23.8 GB 25.9 GB
Too big Get file →
Q6_K27.7 GB 29.8 GB
Too big Get file →
Q8_035.9 GB 38.0 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (12.51 GB file, 14.6 GB memory). For 16 GB VRAM, Q4_K_M (20.22 GB file, 22.3 GB memory) offers a good balance. For 32 GB VRAM, Q6_K (27.68 GB file, 29.8 GB memory) provides higher quality.

What GPU do you need for MultiPL-T-CodeLlama_34b?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ3_XS (13.9 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.7 GB file, about 29.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.9 GB file, about 38.0 GB in use).

Which MultiPL-T-CodeLlama_34b quant should you choose?

Q4_K_M is the usual starting point for MultiPL-T-CodeLlama_34b: it balances file size and quality well. Here it is a 20.2 GB file.

The Q8_0 file is 35.9 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 12.5 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
Parameters33.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseopenrail
Downloads (HF)1,576
Last updated2024-06-25

Frequently asked questions about MultiPL-T-CodeLlama_34b

How much VRAM does MultiPL-T-CodeLlama_34b need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 20.2 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 MultiPL-T-CodeLlama_34b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MultiPL-T-CodeLlama_34b GGUF?

It depends on the quant: Q2_K is 12.5 GB, IQ3_XS is 13.9 GB, Q3_K_S is 14.6 GB, IQ3_S is 14.7 GB, IQ3_M is 15.2 GB, Q3_K_M is 16.3 GB and 8 more.

What context length does MultiPL-T-CodeLlama_34b support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download MultiPL-T-CodeLlama_34b GGUF?

The files are on Hugging Face in the mradermacher/MultiPL-T-CodeLlama_34b-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 MultiPL-T-CodeLlama_34b use?

Hugging Face lists the license as openrail. 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 Q2_K on 8 GB VRAM?

Yes, Q2_K requires 14.6 GB memory at 8 k context, which fits in 8 GB VRAM with some overhead.

Does the model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is released under the openrail license.

Other GGUFs of MultiPL-T-CodeLlama_34b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →