GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

arelath/Qwen3-8B-nanoquant-GGUF overview

Experiment 29: Qwen/Qwen3 8B quality benchmark Status: completed Model: Qwen/Qwen3 8B Revision: b968826d9c46dd6066d109eabc6255188de91218 Candidate run: /worksp…

ggufnanoquantquantizedtext-generationbase_model:Qwen/Qwen3-8Bbase_model:quantized:Qwen/Qwen3-8Blicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~2.06 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

1 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
qwen3-8b-nanoquant.ggufGGUFGGUF2.06 GBDownload

Model Details

Model IDarelath/Qwen3-8B-nanoquant-GGUF
Authorarelath
Pipelinetext-generation
Licenseapache-2.0
Base modelQwen/Qwen3-8B
Last modified2026-07-25T14:07:56.000Z

Model README

---

base_model: Qwen/Qwen3-8B

license: apache-2.0

license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE

pipeline_tag: text-generation

tags:

  • gguf
  • nanoquant
  • quantized

base_model_relation: quantized

---

Experiment 29: Qwen/Qwen3-8B quality benchmark

  • Status: completed
  • Model: Qwen/Qwen3-8B
  • Revision: b968826d9c46dd6066d109eabc6255188de91218
  • Candidate run: /workspace/NanoQuant/evidence/029/029-compress-and-benchmark-qwen3-8b
  • Backend: llama.cpp
  • Wall time: 1769.80 seconds

completed means all evaluators returned finite metrics; it is not a BF16-quality acceptance gate.

Protocol

  • WikiText-2: 64 samples × 128 tokens, batch 8
  • WikiText token hash: sha256:e85e3ae8da01294229ac7dfc651f5d44f74eadaff974ad80a5a19779b58fbe0f
  • Tasks: piqa, arc_easy, arc_challenge, hellaswag, winogrande, boolq; first 200 rows, batch 4
  • Tokenizer hash: sha256:af4e928cfa630ef78563f4800a751d568307a7cd4d4f5fd5919de27b0fbfdbc4

Quality results

| Benchmark | Metric | BF16 | NanoQuant | Delta | Ratio |

| --- | --- | ---: | ---: | ---: | ---: |

| WikiText-2 | perplexity ↓ | 23.110475 | 40.599726 | +17.489251 (+75.68%) | 1.7568x |

| piqa | acc_norm ↑ | 0.8000 | 0.5350 | -0.2650 | 0.6687x |

| arc_easy | acc_norm ↑ | 0.8050 | 0.4000 | -0.4050 | 0.4969x |

| arc_challenge | acc_norm ↑ | 0.5350 | 0.3400 | -0.1950 | 0.6355x |

| hellaswag | acc_norm ↑ | 0.6350 | 0.4050 | -0.2300 | 0.6378x |

| winogrande | acc ↑ | 0.7050 | 0.5700 | -0.1350 | 0.8085x |

| boolq | acc ↑ | 0.8550 | 0.6600 | -0.1950 | 0.7719x |

Deployment storage

| Deployable representation | Bytes | Storage savings vs BF16 |

| --- | ---: | ---: |

| BF16 checkpoint tensors | 16,381,516,776 | — |

| NanoQuant GGUF | 2,214,297,824 | 86.48% |

The packed NanoQuant quantized-layer payload is 884,765,160 bytes. The complete GGUF is the comparable deployable artifact and also includes embeddings, the output projection, norms, and metadata.

Quality execution

The BF16 reference uses Transformers. The NanoQuant candidate is evaluated only from the exported GGUF by the pinned llama.cpp runtime; no reconstructed dense or factorized PyTorch candidate is loaded.

| Runtime | Elapsed seconds | Peak dedicated GPU bytes | Peak host bytes |

| --- | ---: | ---: | ---: |

| BF16 Transformers | 34.98 | 18,886,950,912 | 4,983,508,992 |

| NanoQuant llama.cpp GGUF | 1731.46 | unavailable | 2,550,489,088 |

  • GGUF: /workspace/NanoQuant/Results/029/qwen3-8b-nanoquant.gguf
  • GGUF SHA-256: sha256:75d3f4f150195e0c6a7ccd2ce3372f919534fb7ec609f6b9ba52eb71af194253
  • llama.cpp commit: 2927569f318311aded148d76be6b1109664066f5

Provenance

  • Experiment config hash: sha256:993eca2ef6c345d01926e4677e9cf9620c001fa7e61f1ffa207eeaad1e1803cb
  • Launcher: experiments/029-compress-and-benchmark-qwen3-8b.py
  • Candidate identity: {"config_hash":"sha256:9356ea7a7e46c6dc5286ce574c110add86e4fd77b9f0c92dc32f4646888f9dd9","model_hash":"sha256:db9a057024370dc56a8bba76b9f274692c2094615dc4da1497ce830d14707bc6","plan_hash":"sha256-bc87a0d973d42d9bc247fd72660dc76c590ffe29fbf918f1aa8db56e87c4dd8a"}
  • Global tuning: None

Run arelath/Qwen3-8B-nanoquant-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models