LL

phind_phind-codellama-34b-v2

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant14.2 GB
Quick answer

phind_phind-codellama-34b-v2 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 12 quants, from 14.2 GB (Q2_K) to 35.9 GB (Q8_0).

Phind-CodeLlama-34B-v2: 34B parameter coding model in GGUF format

Phind-CodeLlama-34B-v2 is a 34‑billion parameter model fine‑tuned on 1.5B tokens of high‑quality programming data. It supports the Alpaca/Vicuna instruction format and is proficient in multiple programming languages. The model is available in several GGUF quantisations for llama.cpp and other GGUF‑compatible clients.

Good at

  • Python, C/C++, TypeScript, Java coding
  • Instruction‑tuned for code generation
  • Large context length of 16,384 tokens

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License is llama2

Best for

  • Code completion in IDEs
  • Automated code review tools
  • Generating coding tutorials

Who it’s for. Developers and researchers needing a large open‑source coding model. The model is suitable for local deployment via llama.cpp or other GGUF clients.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K14.2 GB 16.3 GB
Too big Get file →
Q3_K_S14.6 GB 16.7 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 →
Q4_019.1 GB 21.2 GB
Too big Get file →
Q4_K_S19.1 GB 21.3 GB
Too big Get file →
Q4_K_M20.2 GB 22.3 GB
Too big Get file →
Q5_023.2 GB 25.3 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 Q4_K (14.21 GB file, ~21.2 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (20.22 GB file, ~22.3 GB memory). For 16 GB VRAM, Q5_K_M (23.84 GB file, ~25.9 GB memory).

What GPU do you need for phind_phind-codellama-34b-v2?

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: no quant fits at an 8K context.
  • 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 phind_phind-codellama-34b-v2 quant should you choose?

Q4_K_M is the usual starting point for phind_phind-codellama-34b-v2: 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 14.2 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 byTheBloke
FamilyLlama
Licensellama2
Downloads (HF)5,260
Last updated2023-09-27

Frequently asked questions about phind_phind-codellama-34b-v2

How much VRAM does phind_phind-codellama-34b-v2 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 phind_phind-codellama-34b-v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phind_phind-codellama-34b-v2 GGUF?

It depends on the quant: Q2_K is 14.2 GB, Q3_K_S is 14.6 GB, Q3_K_M is 16.3 GB, Q3_K_L is 17.8 GB, Q4_0 is 19.1 GB, Q4_K_S is 19.1 GB and 6 more.

What context length does phind_phind-codellama-34b-v2 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 phind_phind-codellama-34b-v2 GGUF?

The files are on Hugging Face in the TheBloke/Phind-CodeLlama-34B-v2-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 phind_phind-codellama-34b-v2 use?

Hugging Face lists the license as llama2. 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 Phind-CodeLlama-34B-v2 on 8 GB VRAM?

Yes, using the Q4_K quantisation which requires about 21.2 GB of VRAM at 8 k context.

Does the model support image input?

No, the model has no vision capabilities.

What instruction format does it accept?

It accepts the Alpaca/Vicuna instruction format.

Other GGUFs of Phind-CodeLlama-34B-v2

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →