Say exactly what is needed to run this, having tested it

README.md

@@ -174,12 +174,25 @@ Space loads a `Q3_K_M` DiT alongside it.
 
 ### Standalone
 
+Five packages and one file. No build step, no custom CUDA kernels, no
+compilation.
+
+```bash
+pip install -r <(curl -sL https://huggingface.co/topabaem/LTX-2.5-Text-Encoder-4bit/resolve/main/requirements.txt)
+```
+
 ```python
 from huggingface_hub import hf_hub_download, snapshot_download
+
+repo = "topabaem/LTX-2.5-Text-Encoder-4bit"
+
+# The loader ships with the weights; put it on the path before importing it.
+import sys, os
+sys.path.insert(0, os.path.dirname(hf_hub_download(repo, "ltx_packed_codec.py")))
+
 from ltx_packed_codec import load_packed_model
 from transformers import AutoTokenizer
 
-repo = "topabaem/LTX-2.5-Text-Encoder-4bit"
 packed = hf_hub_download(repo, "A3.packed.safetensors")
 encoder_dir = snapshot_download(repo, allow_patterns=["encoder-hf/*"]) + "/encoder-hf"
 
@@ -187,11 +200,37 @@ model = load_packed_model(encoder_dir, packed, resident=True)
 tokenizer = AutoTokenizer.from_pretrained(encoder_dir)
 ```
 
-`encoder-hf/` here is config and tokenizer only, 31 MB. **The 26 GB original is
-not needed**: `load_packed_model` builds the skeleton with
-`AutoModel.from_config` and feeds every parameter from the packed file, so
-nothing reads the Lightricks weights. The asset blobs that ship inside the
-original safetensors are already in the packed file as raw BF16.
+Verified end to end in a clean virtualenv containing nothing but those five
+packages, on **torch 2.13.0 / transformers 5.15.1** and on **torch 2.10.0 /
+transformers 5.12.1**. `encoder-hf/` is config and tokenizer only, 31 MB — the
+26 GB original is not needed.
+
+### What your GPU has to support
+
+Nothing unusual. The format needs no fp8 hardware: the group scales are stored
+as `float8_e4m3fn` bytes and converted in software during a CPU-side decode, so
+`float8` here is a container and never an instruction. There is no minimum
+compute capability, no `comfy_kitchen`, no CUDA 13. The resident model is BF16
+and runs on cards with no bf16 tensor cores at all.
+
+**The one real constraint is your torch wheel, not your GPU.** The default wheel
+on PyPI is now a cu130 build and cu130 dropped Volta. Measured on a V100:
+
+| torch build | device | result |
+|---|---|---|
+| 2.13.0+cu130 | CPU | works |
+| 2.13.0+cu130 | V100, sm_70 | **`no kernel image is available`** |
+| 2.10.0+cu128 | V100, sm_70 | works |
+
+That failure arrives at the *first kernel launch*, well after
+`torch.cuda.is_available()` has returned `True`, so it does not look like an
+installation problem. On sm_70 install a cu128 build:
+
+```bash
+pip install torch --index-url https://download.pytorch.org/whl/cu128
+```
+
+Ampere and newer are unaffected — the stock wheel carries kernels for them.
 
 ### ComfyUI