jondurbin_airoboros-c34b-3.1.2 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 14.2 GB (Q2_K) to 35.9 GB (Q8_0).
34B‑parameter Airoboros model with llama‑2 chat format
jondurbin_airoboros-c34b-3.1.2 is a 34 billion‑parameter model built on the airoboros‑3.1 dataset. It uses the llama‑2 chat template and focuses on instruction following, math reasoning, log extraction, anonymization, and chat introspection.
Good at
- Instruction following
- MathJSON reasoning
- Log information extraction
Limits
- Large context size of 16 384 tokens
- Requires high VRAM for full precision
- No vision support
Best for
- Generating MathJSON solutions
- Extracting data from logs
- Creating anonymized text
Who it’s for. Developers and researchers needing a general‑purpose instruction‑following model with strong math and data extraction capabilities. The model is suitable for local deployment via llama.cpp or compatible GUIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 14.2 GB | 16.3 GB | Too big | Get file → | |
| Q3_K_S | 14.6 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_M | 16.3 GB | 18.4 GB | Too big | Get file → | |
| Q3_K_L | 17.8 GB | 19.9 GB | Too big | Get file → | |
| Q4_0 | 19.1 GB | 21.2 GB | Too big | Get file → | |
| Q4_K_S | 19.1 GB | 21.3 GB | Too big | Get file → | |
| Q4_K_M | 20.2 GB | 22.3 GB | Too big | Get file → | |
| Q5_0 | 23.2 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_S | 23.2 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 23.8 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 27.7 GB | 29.8 GB | Too big | Get file → | |
| Q8_0 | 35.9 GB | 38.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K (16.3 GB memory at 8 k context) or Q3_K_S (16.7 GB). For 12 GB VRAM, Q4_K_M (22.3 GB) or Q5_K_S (25.3 GB) are suitable. Higher quants like Q6_K or Q8_0 require 30 GB+ VRAM.
What GPU do you need for jondurbin_airoboros-c34b-3.1.2?
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 (20.2 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 jondurbin_airoboros-c34b-3.1.2 quant should you choose?
Q4_K_M is the usual starting point for jondurbin_airoboros-c34b-3.1.2: 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 14.2 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
Source
Frequently asked questions about jondurbin_airoboros-c34b-3.1.2
How much VRAM does jondurbin_airoboros-c34b-3.1.2 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 jondurbin_airoboros-c34b-3.1.2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of jondurbin_airoboros-c34b-3.1.2 GGUF?
It depends on the quant: Q2_K is 14.2 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 19.1 GB and 6 more.
What context length does jondurbin_airoboros-c34b-3.1.2 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 jondurbin_airoboros-c34b-3.1.2 GGUF?
The files are on Hugging Face in the TheBloke/Airoboros-c34B-3.1.2-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_airoboros-c34b-3.1.2 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 this model on 8 GB VRAM?
Yes, with Q4_K or Q3_K_S quantisation, which use about 16–17 GB memory at 8 k context.
Does it support image input?
No, the model has no vision capabilities.
What prompt format does it use?
It uses the llama‑2 chat template, not the vicuna style.