BA

bagel 34b v0.5

BagelGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant13.4 GB
Quick answer

bagel 34b v0.5 needs about 23.7 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 13.4 GB (Q2_K) to 37.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Bagel 34b v0.5 – a 34.4B llama model fine‑tuned for long‑context and coding

Bagel 34b v0.5 is a 34.4B llama model fine‑tuned on a wide range of instruction and coding datasets. It supports up to 200000 context tokens and is available in multiple GGUF quantizations. The model is released under an other license.

Good at

  • Long‑context instruction following
  • Coding and function calling
  • Role‑play and tool usage

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License is other, not permissive

Best for

  • Developers building code assistants
  • Researchers testing long‑context models
  • Chatbots needing extended dialogue history

Who it’s for. The model is suited for users who need a large, instruction‑tuned llama model with strong coding and role‑play capabilities. It is ideal for developers and researchers with sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.4 GB 15.9 GB
Too big Get file →
IQ3_XS14.8 GB 17.3 GB
Too big Get file →
Q3_K_S15.5 GB 18.0 GB
Too big Get file →
IQ3_S15.6 GB 18.1 GB
Too big Get file →
IQ3_M16.1 GB 18.6 GB
Too big Get file →
Q3_K_M17.2 GB 19.7 GB
Too big Get file →
Q3_K_L18.7 GB 21.2 GB
Too big Get file →
IQ4_XS19.2 GB 21.7 GB
Too big Get file →
Q4_K_S20.1 GB 22.7 GB
Too big Get file →
Q4_K_M21.2 GB 23.7 GB
Too big Get file →
Q5_K_S24.2 GB 26.8 GB
Too big Get file →
Q5_K_M24.9 GB 27.4 GB
Too big Get file →
Q6_K28.8 GB 31.3 GB
Too big Get file →
Q8_037.0 GB 39.5 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (13.37 GB file, ~15.9 GB memory). For 12 GB VRAM, Q4_K_S (20.14 GB file, ~22.7 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (24.86 GB file, ~27.4 GB memory) offers higher quality. Memory estimates are approximate.

What GPU do you need for bagel 34b v0.5?

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 (13.4 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.8 GB file, about 31.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.0 GB file, about 39.5 GB in use).

Which bagel 34b v0.5 quant should you choose?

Q4_K_M is the usual starting point for bagel 34b v0.5: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 37.0 GB, about 1.7 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 13.4 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 bymradermacher
FamilyBagel
Licenseother
Downloads (HF)1,959
Last updated2024-05-06

Frequently asked questions about bagel 34b v0.5

How much VRAM does bagel 34b v0.5 need?

About 23.7 GB at Q4_K_M with an 8K context window. That is the 21.2 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 bagel 34b v0.5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of bagel 34b v0.5 GGUF?

It depends on the quant: Q2_K is 13.4 GB, IQ3_XS is 14.8 GB, Q3_K_S is 15.5 GB, IQ3_S is 15.6 GB, IQ3_M is 16.1 GB, Q3_K_M is 17.2 GB and 8 more.

What context length does bagel 34b v0.5 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 bagel 34b v0.5 GGUF?

The files are on Hugging Face in the mradermacher/bagel-34b-v0.5-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 bagel 34b v0.5 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 v0.5 on 8 GB VRAM?

Use the Q2_K quant, which requires about 15.9 GB of VRAM at 8 k context. 8 GB VRAM is insufficient for this quant.

Does Bagel 34b v0.5 support image inputs?

No, the model has no vision capabilities.

What is the maximum context length for Bagel 34b v0.5?

The model was trained with 200000 context tokens.

Other GGUFs of bagel-34b-v0.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bagel models

All Bagel →

Other large models

All large models →