Llama-4-Maverick-17B-128E-Instruct needs about 244.9 GB of memory at Q4_K_M (a 242.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 105.7 GB (TQ1_0) to 801.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
17B Llama‑4 Maverick with 128‑expert MoE and multimodal support
Llama‑4 Maverick is a 17 billion‑parameter, 128‑expert mixture‑of‑experts model. It supports text and image inputs and outputs multilingual text and code. The model offers a 1 M token context length and was trained on a large multimodal dataset.
Good at
- Multimodal text and image understanding
- Large context handling
- Efficient inference with MoE
Limits
- Requires large VRAM for full‑precision runs
- No native vision support in current GGUF releases
- License is other, not open source
Best for
- Developers building multimodal chatbots
- Researchers testing MoE architectures
- Applications needing long‑context reasoning
Who it’s for. Engineers and researchers who need a large, multimodal language model with a mixture‑of‑experts architecture. The model is suitable for environments that can accommodate its memory demands.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 105.7 GB | 107.8 GB | Too big | Get file → | |
| IQ1_S | 120.8 GB (3 parts) | 122.9 GB | Too big | Get file → | |
| IQ1_M | 127.5 GB (3 parts) | 129.7 GB | Too big | Get file → | |
| IQ2_XXS | 135.2 GB (3 parts) | 137.3 GB | Too big | Get file → | |
| IQ2_M | 141.2 GB (3 parts) | 143.3 GB | Too big | Get file → | |
| Q2_K | 145.6 GB (3 parts) | 147.8 GB | Too big | Get file → | |
| Q2_K_L | 145.9 GB (3 parts) | 148.0 GB | Too big | Get file → | |
| Q2_K_XL | 152.7 GB (4 parts) | 154.8 GB | Too big | Get file → | |
| IQ3_XXS | 169.3 GB (4 parts) | 171.4 GB | Too big | Get file → | |
| Q3_K_S | 172.7 GB (4 parts) | 174.8 GB | Too big | Get file → | |
| Q3_K_XL | 179.6 GB (4 parts) | 181.7 GB | Too big | Get file → | |
| Q3_K_M | 191.1 GB (4 parts) | 193.2 GB | Too big | Get file → | |
| IQ4_XS | 214.3 GB (5 parts) | 216.4 GB | Too big | Get file → | |
| IQ4_NL | 225.8 GB (5 parts) | 227.9 GB | Too big | Get file → | |
| Q4_0 | 226.8 GB (5 parts) | 228.9 GB | Too big | Get file → | |
| Q4_K_S | 227.8 GB (5 parts) | 229.9 GB | Too big | Get file → | |
| Q4_K_XL | 232.1 GB (5 parts) | 234.2 GB | Too big | Get file → | |
| Q4_K_M | 242.8 GB (5 parts) | 244.9 GB | Too big | Get file → | |
| Q4_1 | 250.7 GB (6 parts) | 252.8 GB | Too big | Get file → | |
| Q5_K_S | 275.7 GB (6 parts) | 277.8 GB | Too big | Get file → | |
| Q5_K_M | 284.5 GB (6 parts) | 286.6 GB | Too big | Get file → | |
| Q5_K_XL | 287.0 GB (6 parts) | 289.1 GB | Too big | Get file → | |
| Q6_K | 328.8 GB (7 parts) | 330.9 GB | Too big | Get file → | |
| Q6_K_XL | 341.1 GB (8 parts) | 343.2 GB | Too big | Get file → | |
| Q8_0 | 425.8 GB (9 parts) | 427.9 GB | Too big | Get file → | |
| Q8_K_XL | 460.0 GB (10 parts) | 462.1 GB | Too big | Get file → | |
| BF16 | 801.5 GB (18 parts) | 803.6 GB | Too big | Get file → |
For 8 GB VRAM use Q4_0 (≈229 GB memory at 8k context). For 16 GB VRAM use Q4_K_M (≈245 GB). For 24 GB VRAM use Q4_K_XL (≈234 GB). Larger quants require more memory.
What GPU do you need for Llama-4-Maverick-17B-128E-Instruct?
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 Llama-4-Maverick-17B-128E-Instruct quant should you choose?
Q4_K_M is the usual starting point for Llama-4-Maverick-17B-128E-Instruct: it balances file size and quality well. Here it is a 242.8 GB file.
The Q8_0 file is 425.8 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 TQ1_0 at 105.7 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Llama-4-Maverick-17B-128E-Instruct
How much VRAM does Llama-4-Maverick-17B-128E-Instruct need?
About 244.9 GB at Q4_K_M with an 8K context window. That is the 242.8 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 Llama-4-Maverick-17B-128E-Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 107.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama-4-Maverick-17B-128E-Instruct GGUF?
It depends on the quant: TQ1_0 is 105.7 GB, IQ1_S is 120.8 GB, IQ1_M is 127.5 GB, IQ2_XXS is 135.2 GB, IQ2_M is 141.2 GB, Q2_K is 145.6 GB and 21 more.
What context length does Llama-4-Maverick-17B-128E-Instruct 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 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Llama-4-Maverick-17B-128E-Instruct GGUF?
The files are on Hugging Face in the unsloth/Llama-4-Maverick-17B-128E-Instruct-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 Llama-4-Maverick-17B-128E-Instruct 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 Llama‑4 Maverick on 8 GB VRAM?
Use the Q4_0 quant, which estimates about 229 GB of VRAM at 8k context. This is the lowest‑memory option available.
Does the model support image input?
Yes, the model is natively multimodal and accepts image inputs, but current GGUF releases support text only.
What is the maximum context length?
The model supports up to 1 M tokens of context.