中文Sign up

AtomicChat/Qwen3-8B-DFlash-GGUF

🤗 Hugging Face sourcetext-generationmit8B activated3.2 GBGGUF✓ 2 checksumsupdated today
Needs seeder →
Base model: z-lab/Qwen3-8B-DFlash-b16

Qwen3 8B Dflash b16, self-quantized to GGUF by Atomic Chat. Built straight from Z Lab's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline.

Highlights

  • 1.0B parameters: the weights this repo quantizes.
  • Context length: 40,960 tokens (40K), as published by Z Lab.
  • 5 layers: Dense decoder.
  • Full imatrix ladder: every quant is calibrated with an importance matrix.

[!NOTE] These GGUFs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.

[!IMPORTANT] Always pass --jinja so the Qwen3 8B Dflash b16 chat template is applied. Without it the model can emit malformed turns.

Model Overview

Property Value
Base model z-lab/Qwen3-8B-DFlash-b16
Parameters 1.0B
Layers 5
Context length 40,960 tokens (40K)
Vocabulary 151,936
Modalities Text
Architecture Dense decoder, 32 attention heads over 8 KV heads, DFlashDraftModel
This repo GGUF quants (imatrix). Quants: Q8_0

Choosing a quant

Quant Size Notes
Q8_0 1.1 GB Effectively lossless, reference quality.

[!TIP] Pick the largest file that fits your (V)RAM with room for context. Q8_0 is the sweet spot for most setups; Q6_K or Q8_0 for maximum fidelity.

Get started

Run Qwen3 8B Dflash b16 locally with:

  • Atomic Chat: the easiest path. Open the app, search AtomicChat/Qwen3-8B-DFlash-GGUF, pick a quant, hit Use this model.
  • llama.cpp: llama-server -hf AtomicChat/Qwen3-8B-DFlash-GGUF:Q8_0 --jinja -c 8192
  • Ollama: ollama run hf.co/AtomicChat/Qwen3-8B-DFlash-GGUF:Q8_0
  • LM Studio / Jan: search the repo id, download any quant.

Best practices

Parameter Value
temperature 0.0

Z Lab's recommended sampling configuration for z-lab/Qwen3-8B-DFlash-b16.

Run in llama.cpp

git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server

./llama.cpp/build/bin/llama-server \
    -hf AtomicChat/Qwen3-8B-DFlash-GGUF:Q8_0 \
    --jinja -ngl 99 -c 8192 -fa on

How these were made

  1. Download z-lab/Qwen3-8B-DFlash-b16 (original weights).
  2. Convert to f16 GGUF with llama.cpp.
  3. Build an importance matrix over our calibration corpus.
  4. Quantize the ladder with --imatrix.

License

Original model by Z Lab, released under the MIT license. Quantized by Atomic Chat.