BE

34b beta

BetaGGUF by MaziyarPanahiUpdated 2024-03-04
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant12.8 GB
Quick answer

34b beta needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 12.8 GB (Q2_K) to 36.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

34b beta – a 34.4B llama model in GGUF format

34b beta is a 34.4B parameter llama model released under GPL‑3.0. It is available in multiple quantizations and can be run with llama.cpp or other GGUF‑compatible clients. The model was trained on 200 000 context tokens and is not a mixture of experts.

Good at

  • Large context handling
  • High‑parameter language modeling
  • Versatile quantization options

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Precision issues may affect output quality

Best for

  • Local inference on GPUs
  • Fine‑tuning with llama.cpp
  • Running in web UI environments

Who it’s for. Developers and researchers who need a large llama model for local deployment and are comfortable with GGUF quantizations. The GPL‑3.0 license allows modification and redistribution under the same terms.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.8 GB 15.3 GB
Too big Get file →
Q3_K_S15.0 GB 17.5 GB
Too big Get file →
Q3_K_M16.7 GB 19.2 GB
Too big Get file →
Q3_K_L18.1 GB 20.7 GB
Too big Get file →
Q4_K_S19.6 GB 22.1 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q5_K_S23.7 GB 26.2 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q6_K28.2 GB 30.7 GB
Too big Get file →
Q8_036.5 GB 39.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 19.6 GB, estimated 22.1 GB memory). For 16 GB VRAM, Q5_K_M (24.32 GB, 26.8 GB memory) is suitable. If more VRAM is available, Q8_0 (36.54 GB, 39.1 GB memory) offers the best quality.

What GPU do you need for 34b beta?

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 (12.8 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).

Which 34b beta quant should you choose?

Q4_K_M is the usual starting point for 34b beta: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.5 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 12.8 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
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byMaziyarPanahi
FamilyBeta
Licensegpl-3.0
Downloads (HF)1,573
Last updated2024-03-04

Frequently asked questions about 34b beta

How much VRAM does 34b beta need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 34b beta on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of 34b beta GGUF?

It depends on the quant: Q2_K is 12.8 GB, Q3_K_S is 15.0 GB, Q3_K_M is 16.7 GB, Q3_K_L is 18.1 GB, Q4_K_S is 19.6 GB, Q4_K_M is 20.7 GB and 4 more.

What context length does 34b beta support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download 34b beta GGUF?

The files are on Hugging Face in the MaziyarPanahi/34b-beta-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 34b beta use?

Hugging Face lists the license as gpl-3.0. 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 34b beta on 8 GB VRAM?

Yes, using Q4_K_S quantization. It requires about 22.1 GB of VRAM at 8 k context, so a 8 GB GPU will need off‑load or CPU fallback.

Does 34b beta support vision tasks?

No, the model has no vision capabilities.

What inference framework should I use?

Use llama.cpp or a GGUF‑compatible client; avoid accelerated frameworks like VLLM due to precision issues.

Other GGUFs of 34b-beta

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Beta models

All Beta →

Other large models

All large models →