BA

jondurbin_bagel-34b-v0.2

BagelGGUF by TheBlokeUpdated 2024-01-02
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant14.6 GB
Quick answer

jondurbin_bagel-34b-v0.2 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 12 quants, from 14.6 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.

Bagel 34B v0.2 – a 34.4B‑parameter LLM fine‑tuned for coding and roleplay

Bagel 34B v0.2 is a 34.4B‑parameter model fine‑tuned from yi‑34b‑200k. It is optimized for creative writing, roleplay and coding tasks. The model is available in multiple GGUF quantisations for local deployment.

Good at

  • Creative roleplay
  • Coding assistance
  • Long‑form text generation

Limits

  • No vision support
  • Requires 8 k context for estimates
  • License type: other

Best for

  • Story writers needing detailed dialogue
  • Developers looking for code generation
  • Chatbots with roleplay scenarios

Who it’s for. Users who want a large, versatile model for text‑only tasks and can run it locally or on a rented GPU VM. The model is suitable for developers, writers, and hobbyists who prefer a fine‑tuned LLM with strong coding and roleplay capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K14.6 GB 17.1 GB
Too big Get file →
Q3_K_S15.0 GB 17.5 GB
Too big Get file →
Q3_K_M16.6 GB 19.2 GB
Too big Get file →
Q3_K_L18.1 GB 20.7 GB
Too big Get file →
Q4_019.5 GB 22.0 GB
Too big Get file →
Q4_K_S19.5 GB 22.1 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q5_023.7 GB 26.2 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_0 (file size 19.47 GB, estimated 22 GB memory). For 12 GB VRAM, Q4_K_M (20.66 GB, 23.2 GB). For 16 GB VRAM, Q5_K_M (24.32 GB, 26.8 GB). Higher quants provide better quality but need more memory.

What GPU do you need for jondurbin_bagel-34b-v0.2?

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 (20.7 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 jondurbin_bagel-34b-v0.2 quant should you choose?

Q4_K_M is the usual starting point for jondurbin_bagel-34b-v0.2: 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 14.6 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 byTheBloke
FamilyBagel
Licenseother
Downloads (HF)338
Last updated2024-01-02

Frequently asked questions about jondurbin_bagel-34b-v0.2

How much VRAM does jondurbin_bagel-34b-v0.2 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 jondurbin_bagel-34b-v0.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of jondurbin_bagel-34b-v0.2 GGUF?

It depends on the quant: Q2_K is 14.6 GB, Q3_K_S is 15.0 GB, Q3_K_M is 16.6 GB, Q3_K_L is 18.1 GB, Q4_0 is 19.5 GB, Q4_K_S is 19.5 GB and 6 more.

What context length does jondurbin_bagel-34b-v0.2 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 jondurbin_bagel-34b-v0.2 GGUF?

The files are on Hugging Face in the TheBloke/bagel-34b-v0.2-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 jondurbin_bagel-34b-v0.2 use?

Hugging Face lists the license as other. 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 Bagel 34B v0.2 on 8 GB VRAM?

Yes, using the Q4_0 quantisation which requires approximately 22 GB of VRAM at 8 k context. It will fit on 8 GB VRAM with swap or lower context.

Does the model support image inputs?

No, Bagel 34B v0.2 is a text‑only model and does not support vision.

What context length does the model support?

The model was trained on 200 000 tokens and supports up to 8 k context for inference.

Other GGUFs of bagel-34b-v0.2

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Bagel models

All Bagel →

Other large models

All large models →