Edge0-145B's selling point is not the parameter count itself but an architecture rewritten for one consumer computer: 145B total parameters with only 10.12B active per token, 48 layers with 512 experts each, a 51.2B-parameter n-gram embedding table, and a three-tier GPU / system-memory / SSD pipeline. This article works through the Hugging Face model card (read directly by this site on Nov 16, 2026) item by item — every number comes from the model card or the official blog, the technical report is still unpublished, and no third party has reproduced any of it yet.
| Component | Size | Notes |
|---|---|---|
| Total parameters | 145B | 10.12B active per token — about 7% of parameters take part in a single step |
| Expert pool | 84.6B parameters | Latent width ℓ=1792; each expert is a fixed 1.63 MB record |
| N-gram embedding table (PLE) | 51.2B parameters | fp8, memory-mapped from SSD; about a third of all parameters |
| MTP speculative-decoding head | 1.26B | Draft model with 512 experts, for speculative decoding |
| Rest (attention, vocabulary, etc.) | About 7.9B | Residual after the three items above |
Read the composition first: expert pool 84.6B + n-gram table 51.2B + MTP head 1.26B ≈ 137B, leaving about 7.9B. More than a third of the parameters sit not in MoE experts but in an n-gram table mapped from SSD — the biggest structural difference between Edge0-145B and a conventional MoE.
Edge0-145B is a latent sparse MoE: 48 layers, 512 experts per layer, 10 routed experts + 1 shared expert active per token, SwiGLU width 640. Per the model card, the MoE expert layers were rebuilt — the base Qwen3.8-Flash-Next's routed experts were replaced by latent MoE in all 48 layers — and the model was post-trained afterwards on Edge0's own data. Attention is hybrid: full attention every 4 layers, with a sparse indexer on the rest.
Why "latent": experts do not sit in VRAM as full weight matrices. Each lives in the expert pool as a fixed 1.63 MB record, fetched on demand. Combined with the sparsity of 10 active experts per token, compute per step is held to 10.12B active parameters — the whole meaning of "a 145B model at 10B-scale compute". The cost is movement outside VRAM: expert records stream in from system memory or SSD, so speed depends on the pipeline, not on raw compute.
Edge0-145B does not run by loading the model into VRAM. It splits the work across three tiers: the GPU holds only what the current computation needs, system memory holds the expert library, and the SSD holds the n-gram vocabulary data. The model card's measured residency (RTX 5090 D 24GB) is: NVFP4 at 23.25 GiB VRAM + 38.27 GiB host RAM, Q3_K at 23.14 GiB VRAM + 31.28 GiB host RAM — plus an expert library of about 40GB in system memory and vocabulary data of about 48GB on SSD. The blog headline's "29GB peak memory" is GPU-side peak only: whole-machine demand is about 61.5 GiB for NVFP4 and about 54.4 GiB for Q3_K. See our install guide.
The point of the pipeline is a shifted threshold: it trades "needs 145B of VRAM" for "needs one 16GB+ VRAM GPU + 31–38 GiB of system RAM + about 40–48 GiB of disk". Good news for anyone with a big-memory desktop; not good news for a thin laptop with 16GB of unified memory — it fails the system-RAM test before it starts.
According to Edge0, Edge0-145B was trained natively at 4 bits in the on-device architecture from the outset — not a post-hoc quantization of a cloud model. If true, that explains why it ships directly in two 4-bit builds, Q3_K and NVFP4: the weights were laid out at low precision during training, not trained in FP16 and squeezed afterwards. But note: this is the vendor's claim, the technical report is still unpublished, and training details (data volume, training steps, precision-loss comparisons) cannot be verified today. The two builds' measured speeds confirm the other side of "native" — Q3_K runs faster than NVFP4 (121.2 vs 98.3 tok/s agent decode), trading lower precision for higher throughput.
The context window is 256K tokens, with the KV cache in int8 and 32K resident. 256K is long for an on-device model — still short of the 1M cloud flagships, but enough for local agent work such as reading a code base or long-document Q&A. Int8 KV follows the same idea: squeeze VRAM further to buy a longer usable context. One caveat: the model card publishes no speed decay or accuracy figures at a full 256K load, so real long-context usability awaits independent testing.
Input is text + image: the model folder carries a vision encoder, mmproj-BF16.gguf, but it needs the strata-vision helper and is not built from the Edge0 tree; output is text. Tool calling runs through the local OpenAI- / Anthropic-compatible server. In other words, vision and tool calling both exist, but the vision path needs an extra component — the launch-week documentation does not spell that out clearly, so check the strata-vision status before installing.
| Build (RTX 5090 D 24GB, vendor-measured) | Agent decode | 16K prefill | VRAM / host RAM |
|---|---|---|---|
| NVFP4 (47.79 GiB) | 98.3 tok/s | 3,165.7 tok/s | 23.25 / 38.27 GiB |
| Q3_K (40.81 GiB) | 121.2 tok/s | 3,554.9 tok/s | 23.14 / 31.28 GiB |
There is also a Metal measurement on Apple M2 Ultra: Q3_K at 57.0 tok/s agent decode — note this is a Metal speed measurement, not proof of macOS availability; the GitHub README's platform table lists no macOS support for the 145B/120B models at launch. See the install guide. The blog's headline figures (80+ tok/s decode, 1,100+ tok/s prefill, ~120W typical power) are a lower-bound summary across both builds — quote them with the build name and hardware.
Reference: Hugging Face — Edge0/Edge0-145B-q3k model card · Hugging Face — Edge0/Edge0-145B-NVFP4 model card · Edge0 — Official blog "Introducing Edge0-145B: Frontier AI Capabilities on Your Own Computer" · GitHub — Edge0-AI/Edge0 (rewritten and organized by ModelBrief; facts per official sources)