--- license: other license_name: edge0-community-model-1.0 license_link: LICENSE library_name: edge0 tags: - moe - edge-inference - latent-moe - 4-bit - agent - coding - cuda base_model: - Qwen/Qwen3.8-Flash-Next pipeline_tag: text-generation ---
A 145B agent, running on one consumer GPU.
98.3 tok/s agent decode · 3165.7 tok/s 16K prefill · 86.5 terminal-bench 2.1.
Throughput measured on RTX 5090 D 24 GB · NVFP4.
A latent sparse MoE: 48 layers, 512 experts, 10 active per token, 256K context, trained natively at 4 bits.
This repository: Edge0-145B · NVFP4
ⓘ With residency enabled, 145B NVFP4 used 23.25 GiB VRAM + 38.27 GiB host RAM on RTX 5090 D 24 GB.
NVFP4 · RTX 5090 D 24 GB. Prefill throughput uses a 16K-token input; weight sizes are listed separately for each format.
Higher is better. Results are listed by model.
Throughput is shown in tok/s, grouped by hardware and build. The summary above uses NVFP4 on RTX 5090 D 24 GB.
Highlighted rows show the NVFP4 build in this repository.
| Machine | Build | 4K prefill | 16K prefill | Chat decode | Agent decode |
|---|---|---|---|---|---|
| RTX 5090 D 24 GB | Q3_K | 2169.9 | 3554.9 | 99.7 | 121.2 |
| RTX 5090 D 24 GB | NVFP4 | 1839.6 | 3165.7 | 79.6 | 98.3 |
| RTX 4090 24 GB | Q3_K | 2042.0 | 3179.4 | 69.9 | 91.7 |
| RTX Spark N1X 60 GiB | Q3_K | 674.0 | 770.3 | 37.7 | 36.7 |
| RTX Spark N1X 60 GiB | NVFP4 | 821.2 | 922.4 | 40.1 | 46.0 |
| Apple M2 Ultra (Metal) | Q3_K | 755.6 | 800.3 | 60.9 | 57.0 |
| 16 GiB VRAM + 20 GiB RAM | Q3_K | 249 | 335 | 36.8 | 44.9 |
The 16 GiB VRAM + 20 GiB RAM rows are the same RTX 5090 D 24 GB, not a different card. VRAM is capped with --vram-reserve-mib 8192. System RAM is capped by a cgroup (MemoryMax=20G, no swap). With residency on, the same card holds Q3_K (40.81 GiB of weights)
as 23.14 GiB VRAM + 31.28 GiB RAM, and NVFP4 (47.79 GiB) as 23.25 GiB VRAM + 38.27 GiB RAM — disjoint expert sets,
nothing counted twice.
See Usage & troubleshooting for memory-saving options.
| Edge0-145B | |
|---|---|
| Total parameters | 145B · 10.12 B active per token |
| Layers | 48 · hybrid attention, full every 4 layers + sparse indexer |
| Experts | 512 per layer, 10 routed + 1 shared active per token, SwiGLU width 640 |
| Expert pool | 84.6 B parameters at latent width ℓ = 1792 |
| PLE | 51.2 B n-gram embedding table, fp8, memory-mapped |
| MTP head | 1.26 B draft model, 512 experts, for speculative decode |
| Context | 256K · KV int8 with 32K resident |
| Builds | Q3_K 40.81 GiB · NVFP4 47.79 GiB |
Left: the stack the model actually runs — token embedding, 48 hybrid-attention layers, final norm, lm_head. Right: one layer opened up. Attention reads and writes the full 2560 width. D then projects the token down to ℓ per routing group, the router picks 10 of 512 experts, each expert runs ℓ → 640 → ℓ, a shared expert runs alongside, and U projects the combined result back to 2560.
Everything outside the expert pool stays at 2560: D and U are shared, one copy per layer. Only the 512 experts work at ℓ. That is why an expert is a fixed 1,630,720 B record — the engine keeps a few thousand of them on the card and streams the rest from host memory, at a cost that tracks how many experts are resident and not how big the model is.
Each model folder (Q3_K or NVFP4, Edge0-145B or Edge0-120B) runs on Edge0
through edge0-infer, from the command line or from the Edge0 Chat desktop app. Keep the folder as it is:
edge0-infer identifies the model by model_name in its model.json.
The build instructions cover NVIDIA GPUs with CUDA 13 on Linux or Windows (x64 or ARM64), and Metal on Apple Silicon macOS for the Q3_K build; the NVFP4 build is CUDA-only.
1. Build. Clone the repository, then build two parts:
git clone https://github.com/Edge0-AI/Edge0.git edge0
2. Run from the command line. Pass one model folder, such as Edge0-145B-NVFP4, not the folder that holds several of
them. On Windows the program is build\windows\bin\edge0-infer.exe.
build/cpu/bin/edge0-infer serve --model /path/to/Edge0-145B-NVFP4
It prints Listening: http://127.0.0.1:8000 model=<name> once the weights are loaded, where <name> is edge0_145b,
and then serves OpenAI- and Anthropic-compatible endpoints:
curl localhost:8000/v1/chat/completions -H 'content-type: application/json' -d '{"model":"edge0_145b","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
edge0-infer chat --model /path/to/Edge0-145B-NVFP4 opens an interactive session instead. More options:
edge0-infer/docs/edge0-145b.md.
⬇️ Download: GitHub Releases
Open Edge0 Chat on Windows and choose a model folder, such as Edge0-145B-NVFP4, to run the model locally. To build the app from source, follow the Edge0 Chat guide.
mmproj-BF16.gguf is the vision encoder: it turns a picture into the embedding rows the language model
reads, and the language model itself is unchanged. Reading pictures also needs a small helper program,
strata-vision. That program is not in this repository and the Edge0 source tree does not
build it, so it comes from one of these two places:
setup.py and strata launch download one and
unpack strata and strata-vision side by side, so an install that ran with --vision
already has the helper next to the engine.tools/vision project lives there, not
in Edge0) and run cmake --build build-vision --target strata-vision, then put the result next to
strata.Then two entries in model.json, next to args:
"exe": "/path/to/strata",
"vision": {
"exe": "/path/to/strata-vision",
"mmproj": "./mmproj-BF16.gguf",
"model": "./model-skeleton.gguf",
"gpu": false,
"max_tokens": 1024
}
"model" is the text backbone this folder already uses."gpu": false runs the encoder on the CPU and takes no VRAM. true runs it on the card and
keeps about 1.4 GB free for it, so the expert cache gets that much less."max_tokens" caps how many tokens one picture becomes. More keeps more detail and takes longer.Add --vision to "args" as well. The server adds it by itself when the config has a
vision section and prints a line saying so; writing it keeps the two in step. Without the helper beside the
engine, a request that carries a picture fails with this server was started without the vision encoder.
The log says images on once the encoder is up. Then send a picture: /image /path/to.png
followed by the question in the terminal chat, or an image_url part over the OpenAI API. That part takes a
data: URL, an http(s) URL or a local file path.
curl localhost:8000/v1/chat/completions -H 'content-type: application/json' -d '{
"model": "edge0_145b",
"messages": [{"role": "user", "content": [
{"type": "text", "text": "What does this picture show?"},
{"type": "image_url", "image_url": {"url": "data:image/png;base64,<base64>"}}
]}],
"max_tokens": 256
}'
Add "reasoning_effort": "none" to get the answer without a thinking pass first; otherwise the reply can
come back empty with the token budget spent on the reasoning.
145B / 120B · Memory options
--mmap-experts — read uncached experts from SSD on demand.--resident-budget-gib 20 --expert-profile expert-profile.bin
Up to 20 GiB of host RAM for the expert cache; uncached experts are read from SSD on demand. Includes --mmap-experts and disjoint GPU/RAM caches automatically.
Required: a static expert profile. Replace expert-profile.bin with your profile path.
--resident-budget-gib 20 caps host-RAM expert caching at 20 GiB, lowered further to fit available memory.--resident-experts or --resident-budget-gib N, with a static --expert-profile.--mmap-experts, --resident-cpu-experts, --resident-pin.We thank the teams behind Qwen3.8-Flash-Next and Strata for sharing their work with the community. Edge0 extends the Strata engine with latent MoE support.
Model license. Edge0-specific contributions are provided under the Edge0 Community Model License 1.0, only to the extent that Edge0 owns or is authorized to license them. Qwen materials remain subject to the Qwen Community License 1.0. Both sets of applicable terms must be followed; see NOTICE and the release scope.
The Edge0 license permits personal use, research, modification, noncommercial sharing, internal use, and commercial use of generated outputs, subject to applicable upstream conditions. Selling or commercially bundling the model, operating a commercial model service, or offering an independent commercial coding or office assistant using it requires a separate written Edge0 license. See LICENSE for the precise scope and exceptions.
Commercial licensing: info@edge0.ai. Edge0 permission does not waive Qwen's separate authorization or attribution requirements. Framework code retains its Apache-2.0 license; Strata retains its MIT license. Existing valid grants are not revoked.