Laguna S 2.1 ROCmFP4 STRIX LEAN needs about 64.8 GB of memory at Q4_0 (a 62.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
118B Mixture-of-Experts model with 1M context and native reasoning
Laguna S 2.1 ROCmFP4 STRIX LEAN is a 118B total parameter Mixture-of-Experts model. It supports 1,048,576-token context and interleaved reasoning with tool calls. The model is optimized for AMD Ryzen AI Max+ 395 hardware.
Good at
- Long-horizon reasoning
- Tool‑enabled coding
- Large context handling
Limits
- Requires ROCmFPX fork, not compatible with upstream llama.cpp
- No vision support
- Large VRAM requirement
Best for
- Agentic coding tasks
- Complex reasoning workflows
- Large‑context document analysis
Who it’s for. Developers building agentic applications that need extensive reasoning and tool integration on AMD GPUs. Researchers requiring a high‑parameter Mixture‑of‑Experts model with a 1M token window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 62.6 GB | 64.8 GB | Too big | Get file → |
The only available GGUF quant is Q4_0 with a file size of 62.65 GB. It requires about 64.8 GB of memory at 8K context. For lower memory budgets, no other quant is provided, so the model cannot be run within a smaller VRAM limit.
What GPU do you need for Laguna S 2.1 ROCmFP4 STRIX LEAN?
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 Laguna S 2.1 ROCmFP4 STRIX LEAN quant should you choose?
Q4_0 (62.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Laguna S 2.1 ROCmFP4 STRIX LEAN
How much VRAM does Laguna S 2.1 ROCmFP4 STRIX LEAN need?
About 64.8 GB at Q4_0 with an 8K context window. That is the 62.6 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 Laguna S 2.1 ROCmFP4 STRIX LEAN on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 64.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Laguna S 2.1 ROCmFP4 STRIX LEAN GGUF?
It depends on the quant: Q4_0 is 62.6 GB.
What context length does Laguna S 2.1 ROCmFP4 STRIX LEAN support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Laguna S 2.1 ROCmFP4 STRIX LEAN GGUF?
The files are on Hugging Face in the kingjones777/Laguna-S-2.1-ROCmFP4-STRIX_LEAN-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 Laguna S 2.1 ROCmFP4 STRIX LEAN 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 Laguna S 2.1 on 8 GB VRAM?
No. The Q4_0 quant requires approximately 64.8 GB of VRAM at 8K context, far exceeding 8 GB.
Is this model compatible with the standard llama.cpp build?
No. It requires the charlie12345/ROCmFPX fork built with HIP + ROCmFP4 kernels.
What license does Laguna S 2.1 use?
It is released under the OpenMDW-1.1 license, which is fully permissive for commercial use.