LL

Samantha 1.11 CodeLlama 34B

LlamaGGUF by second-stateUpdated 2024-03-20
Download on Hugging Face
Parameters33.7B
Context2K
Layers48
Architecturellama
Smallest quant12.5 GB
Quick answer

Samantha 1.11 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 12 quants, from 12.5 GB (Q2_K) to 35.9 GB (Q8_0).

Samantha 1.11 CodeLlama 34B – a 33.7B parameter coding assistant

Samantha 1.11 CodeLlama 34B is a 33.7B parameter model trained on CodeLlama‑34b. It specializes in coding tasks and follows the Vicuna‑1.1 chat format. The model is released under the llama2 license and can be run locally with llama.cpp.

Good at

  • Coding assistance
  • Python code generation
  • Algorithm explanations

Limits

  • No vision support
  • Context limited to 2048 tokens
  • Requires llama2 license compliance

Best for

  • Writing boilerplate code
  • Debugging snippets
  • Learning new programming concepts

Who it’s for. Developers and students who need a coding companion. The model is suitable for educational and professional use within the limits of the llama2 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.5 GB 13.4 GB
Too big Get file →
Q3_K_S14.6 GB 15.5 GB
Too big Get file →
Q3_K_M16.3 GB 17.2 GB
Too big Get file →
Q3_K_L17.8 GB 18.7 GB
Too big Get file →
Q4_019.1 GB 20.0 GB
Too big Get file →
Q4_K_S19.2 GB 20.1 GB
Too big Get file →
Q4_K_M20.2 GB 21.1 GB
Too big Get file →
Q5_023.2 GB 24.1 GB
Too big Get file →
Q5_K_S23.2 GB 24.1 GB
Too big Get file →
Q5_K_M23.8 GB 24.7 GB
Too big Get file →
Q6_K27.7 GB 28.6 GB
Too big Get file →
Q8_035.9 GB 36.8 GB
Too big Get file →

For 8 GB VRAM, Q2_K (12.51 GB) or Q3_K_S (14.61 GB) are suitable, with estimated memory at 8 k context of 14.6 GB and 16.7 GB respectively. For 16 GB VRAM, Q4_K_M (20.22 GB) or Q5_K_M (23.84 GB) provide a balance between size and performance. Larger models like Q8_0 (35.86 GB) require 38 GB memory at 8 k context.

What GPU do you need for Samantha 1.11 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 Q2_K (12.5 GB file, about 14.6 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 Samantha 1.11 CodeLlama 34B quant should you choose?

Q4_K_M is the usual starting point for Samantha 1.11 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 context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized bysecond-state
FamilyLlama
Licensellama2
Downloads (HF)1,063
Last updated2024-03-20

Frequently asked questions about Samantha 1.11 CodeLlama 34B

How much VRAM does Samantha 1.11 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 Samantha 1.11 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 Samantha 1.11 CodeLlama 34B GGUF?

It depends on the quant: Q2_K is 12.5 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 19.2 GB and 6 more.

What context length does Samantha 1.11 CodeLlama 34B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download Samantha 1.11 CodeLlama 34B GGUF?

The files are on Hugging Face in the second-state/Samantha-1.11-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 Samantha 1.11 CodeLlama 34B 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 Samantha 1.11 CodeLlama 34B on 8 GB VRAM?

The smallest quantized file is Q2_K at 12.51 GB, which exceeds 8 GB VRAM. You would need at least 14.6 GB memory at 8 k context to run it comfortably.

Does this model support image input?

No, Samantha 1.11 CodeLlama 34B does not have vision capabilities.

What license applies to this model?

The model is released under the llama2 license, allowing commercial and non‑commercial use within its limits.

Other GGUFs of Samantha-1.11-CodeLlama-34b

Similar models

Browse all →

More from second-state

All by second-state →

More Llama models

All Llama →

Other medium models

All medium models →