TML Inkling needs about 451.0 GB of memory at Q3_K_XL (a 432.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 270.2 GB (IQ1_S) to 1894.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 70.9 GB.
TML Inkling – 950 B multimodal transformer with Mixture‑of‑Experts
TML Inkling is a 950 B multimodal autoregressive transformer. It accepts text, image and audio inputs and outputs text. The model uses a 66‑layer decoder with a sparse Mixture‑of‑Experts backbone, routing each token to 6 of 256 experts.
Good at
- Multimodal reasoning
- Text, image and audio processing
- Large context support
Limits
- Requires 8 k context for full performance
- Large memory footprint for high‑quality quants
- No vision support in low‑bit quants
Best for
- Developers building multimodal assistants
- Chatbots needing image and audio understanding
- Retrieval‑augmented generation with multimodal data
Who it’s for. Developers and researchers who need a general‑purpose multimodal model with open weights. Suitable for building AI applications that require text, image, and audio inputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 270.2 GB (7 parts) | 288.4 GB | Too big | Get file → | |
| IQ1_M | 285.0 GB (7 parts) | 303.3 GB | Too big | Get file → | |
| Q2_K_XL | 317.3 GB (8 parts) | 335.5 GB | Too big | Get file → | |
| Q3_K_XL | 432.8 GB (10 parts) | 451.0 GB | Too big | Get file → | |
| Q4_K_XL | 587.0 GB (14 parts) | 605.3 GB | Too big | Get file → | |
| Q8_0 | 856.8 GB (19 parts) | 875.0 GB | Too big | Get file → | |
| BF16 | 1894.3 GB (41 parts) | 1912.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (270 GB file, ~288 GB memory). For 16 GB VRAM, use Q2_K_XL (317 GB file, ~336 GB memory). For 32 GB VRAM, use Q4_K_XL (587 GB file, ~605 GB memory). Estimates are approximate.
What GPU do you need for TML Inkling?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which TML Inkling quant should you choose?
Q3_K_XL (432.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ1_S at 270.2 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 TML Inkling
How much VRAM does TML Inkling need?
About 451.0 GB at Q3_K_XL with an 8K context window. That is the 432.8 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 TML Inkling on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 288.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of TML Inkling GGUF?
It depends on the quant: IQ1_S is 270.2 GB, IQ1_M is 285.0 GB, Q2_K_XL is 317.3 GB, Q3_K_XL is 432.8 GB, Q4_K_XL is 587.0 GB, Q8_0 is 856.8 GB and 1 more.
What context length does TML Inkling support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 17.7 GB at 8K and 70.9 GB at 32K.
Where can I download TML Inkling GGUF?
The files are on Hugging Face in the unsloth/inkling-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 TML Inkling use?
Hugging Face lists the license as apache-2.0. 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 TML Inkling on 8 GB VRAM?
Use the IQ1_S quant, which requires about 288 GB of VRAM at 8 k context. This is the smallest available quant for this model.
Does TML Inkling support vision?
Yes, the model is natively multimodal and accepts image inputs. However, some low‑bit quants may not fully support vision.
What license applies to TML Inkling?
The model is released under the Apache‑2.0 license, allowing free use and modification.