LL

Phind CodeLlama 34B v2

LlamaGGUF by mradermacherUpdated 2024-09-12
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant12.5 GB
Quick answer

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 14 quants, from 12.5 GB (Q2_K) to 35.9 GB (Q8_0).

Phind CodeLlama 34B v2 – a 33.7B parameter coding model

Phind CodeLlama 34B v2 is a 33.7B parameter Llama model fine‑tuned on 1.5B high‑quality programming tokens. It is instruction‑tuned in the Alpaca/Vicuna format and supports a 16384 token context window. The model is released under the llama2 license.

Good at

  • Python and C/C++ code generation
  • Instruction following in multiple languages
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • Limited safety testing

Best for

  • Developers needing code completion
  • Educational coding assistants
  • Research on code generation

Who it’s for. The model is suited for developers, educators, and researchers who need a high‑capacity coding assistant. It is best used with a GPU that can accommodate the chosen quantization and the 16384 token context window.

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 8–12 GB VRAM, use Q2_K (12.51 GB, 14.6 GB memory at 8k context). For 16–20 GB VRAM, Q4_K_S (19.19 GB, 21.3 GB memory) or Q4_K_M (20.22 GB, 22.3 GB memory). For 24–32 GB VRAM, Q5_K_S (23.24 GB, 25.3 GB memory) or Q5_K_M (23.84 GB, 25.9 GB memory). Memory estimates are approximate.

What GPU do you need for 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: 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 Phind CodeLlama 34B v2 quant should you choose?

Q4_K_M is the usual starting point for 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 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
Licensellama2
Downloads (HF)2,078
Last updated2024-09-12

Frequently asked questions about Phind CodeLlama 34B v2

How much VRAM does 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 CodeLlama 34B v2 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 Phind CodeLlama 34B v2 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 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 CodeLlama 34B v2 GGUF?

The files are on Hugging Face in the mradermacher/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 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?

The smallest quant, Q2_K, is 12.51 GB and requires about 14.6 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does the model support image inputs?

No, the model has no vision capability.

What license applies to this model?

The model is released under the llama2 license.

Other GGUFs of Phind-CodeLlama-34B-v2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →