Llama 4 Scout 17B 16E Instruct Abliterated v2 needs about 39.1 GB of memory at Q2_K_S (a 37.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 13 quants, from 22.2 GB (IQ1_S) to 47.5 GB (IQ3_M). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Llama 4 Scout 17B 16E Instruct Abliterated v2 – 108B parameter Llama‑4 model
Llama‑4 Scout 17B 16E Instruct Abliterated v2 is a 108B parameter model built on the unsloth/Llama‑4‑Scout‑17B‑16E‑Instruct base. It supports a 10 M token context window and offers multiple IQ quants for efficient inference. The model is uncensored and includes vision capabilities via mmproj files.
Good at
- Large context handling
- 108B parameter count
- Uncensored instruction following
Limits
- No license specified
- High VRAM requirement for full precision
- Vision support requires mmproj files
Best for
- Complex instruction generation
- Long‑form content creation
- Research on large Llama‑4 models
Who it’s for. Developers needing a 108B Llama‑4 model with abliteration for instruction tasks. Researchers exploring large language models without censorship.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 22.2 GB | 24.3 GB | Too big | Get file → | |
| IQ1_M | 24.6 GB | 26.7 GB | Too big | Get file → | |
| IQ2_XXS | 28.6 GB | 30.7 GB | Too big | Get file → | |
| IQ2_XS | 31.8 GB | 33.9 GB | Too big | Get file → | |
| IQ2_S | 32.3 GB | 34.4 GB | Too big | Get file → | |
| IQ2_M | 35.5 GB | 37.6 GB | Too big | Get file → | |
| Q2_K_S | 37.0 GB | 39.1 GB | Too big | Get file → | |
| Q2_K | 39.6 GB | 41.7 GB | Too big | Get file → | |
| IQ3_XXS | 41.7 GB | 43.8 GB | Too big | Get file → | |
| IQ3_XS | 44.3 GB | 46.4 GB | Too big | Get file → | |
| Q3_K_S | 46.7 GB | 48.9 GB | Too big | Get file → | |
| IQ3_S | 46.8 GB | 48.9 GB | Too big | Get file → | |
| IQ3_M | 47.5 GB | 49.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (22.18 GB file, 24.3 GB memory). For 12 GB VRAM, IQ1_M or IQ2_XXS. For 16 GB VRAM, IQ2_XS or IQ2_S. Memory estimates are approximate.
What GPU do you need for Llama 4 Scout 17B 16E Instruct Abliterated v2?
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: the best quant that fits is IQ2_XXS (28.6 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_XS (44.3 GB file, about 46.4 GB in use).
Which Llama 4 Scout 17B 16E Instruct Abliterated v2 quant should you choose?
Q2_K_S (37.0 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 22.2 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
Frequently asked questions about Llama 4 Scout 17B 16E Instruct Abliterated v2
How much VRAM does Llama 4 Scout 17B 16E Instruct Abliterated v2 need?
About 39.1 GB at Q2_K_S with an 8K context window. That is the 37.0 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 Llama 4 Scout 17B 16E Instruct Abliterated v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 4 Scout 17B 16E Instruct Abliterated v2 GGUF?
It depends on the quant: IQ1_S is 22.2 GB, IQ1_M is 24.6 GB, IQ2_XXS is 28.6 GB, IQ2_XS is 31.8 GB, IQ2_S is 32.3 GB, IQ2_M is 35.5 GB and 7 more.
What context length does Llama 4 Scout 17B 16E Instruct Abliterated v2 support?
The GGUF header lists a trained context length of 10,485,760 tokens (10240K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Llama 4 Scout 17B 16E Instruct Abliterated v2 GGUF?
The files are on Hugging Face in the mradermacher/Llama-4-Scout-17B-16E-Instruct-abliterated-v2-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
The smallest quant IQ1_S requires about 24.3 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does this model support vision?
The repository indicates it is a vision model; mmproj files may be available.
What generation parameters are recommended?
Use temperature=0.8, top_p=0.75.