Edge0-8B-A1B-preview

ReleasedRelease date unknownSize7.9B tensors · MoERoleAssistantLicenseapache-2.0Context128K config max

Where it runs 8K context · ≥ 5 t/s floor

Setup	Best plan	Memory	Generate
8 GB GPU + 32 GB RAM	native quantizedvLLMFull GPU	KV unknown	Unknown
12 GB GPU + 32 GB RAM	native quantizedvLLMFull GPU	KV unknown	Unknown
16 GB GPU + 64 GB RAM	native quantizedvLLMFull GPU	KV unknown	Unknown
24 GB GPU + 64 GB RAM	native quantizedvLLMFull GPU	KV unknown	Unknown
32 GB GPU + 128 GB RAM	native quantizedvLLMFull GPU	KV unknown	Unknown
2× 24 GB GPUs + 128 GB RAM	native quantizedvLLMFull GPU	KV unknown	Unknown
96 GB workstation GPU + 256 GB RAM	native quantizedvLLMFull GPU	KV unknown	Unknown
Mac, 24 GB	Does not fit
Mac, 48 GB	Does not fit
Mac, 128 GB	Does not fit
Mac, 512 GB	Does not fit
DGX Spark 128 GB	native quantizedvLLMUnified memory	KV unknown	Unknown
Ryzen AI Max+ 395, 128 GB	native quantizedvLLMUnified memory	KV unknown	Unknown
CPU only, 64 GB DDR5-5600 dual channel	Does not fit

Same plan engine as the planner, with its default reserves and RAM. How plans are chosen.

Files exact Hugging Face bytes

Artifact	Size	Files	Revision	Source
Native safetensors mixed/custom native; bits=4; stored tensor dtypes=U32/BF16/F Edge0/Edge0-8B-A1B-preview	4.20 GiB	1	269b9a2c4a	HF files

Not found in the representative quant search (not proven unavailable): GGUF FP16, GGUF Q8_0, GGUF Q5_K_M, GGUF Q4_K_M, MLX 8-bit, MLX 4-bit, EXL3, AWQ, GPTQ. Complete selected file sets; projectors, MTP/draft and lookup files are listed separately and budgeted only by plans that use them. File bytes are not allocated memory.

Quality

No Artificial Analysis evaluation mapped to this checkpoint.

Arena text rating

Unknown

Publisher-reported benchmarks

None extracted from the model card.

AA and Arena describe the hosted model in the stated mode, not each quantized file; scores are never inherited by base, pruned, abliterated or quantized variants and never averaged together.

How to run it

edge0

source-documented, not executed source · publisher edge0 GitHub main at cutoff

pip install -e 'git+https://github.com/Edge0-AI/edge0.git#egg=edge0[fetch]'

# Download this repository into a local directory
huggingface-cli download Edge0/Edge0-8b-a1b-preview --local-dir ./Edge0-8b-a1b-preview

# Run it
export EDGE0_8B_MODEL=$PWD/Edge0-8b-a1b-preview
edge0 chat --name edge0-8b --prompt "Introduce yourself"

# Or serve an OpenAI-compatible HTTP API
edge0 serve --name edge0-8b --port 8083

Recipes are source examples (settings are the publisher’s or author’s, not measured optima) and were not executed by LocalFit. A downloadable file does not prove your backend build supports the architecture.

Reported speeds 0

No reported measurement yet. Submit one.