中文Sign up

groxaxo/Qwen3.5-9B-GLM5.1-Distill-v1-GGUF

🤗 Hugging Face sourceapache-2.09B activated85 GBGGUF✓ 14 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo groxaxo/Qwen3.5-9B-GLM5.1-Distill-v1-GGUF ./model-folder
Needs a seeder →

Qwen3.5-9B-GLM5.1-Distill-v1 — GGUF Quantized

Overview

Qwen3.5-9B-GLM5.1-Distill-v1-GGUF is a GGUF release for llama.cpp-compatible runtimes and local inference, published by groxaxo. It is intended for open-source evaluation, reproducible experimentation, and compatible local or hosted inference workflows. The wording below is deliberately limited to what can be verified from this repository's metadata and artifacts.

At a glance

Field Details
Format GGUF
Source / base Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1
Intended task the task described by the included configuration and documentation
License apache-2.0

What is included

  • *.gguf (13 files)
  • Additional configuration, tokenizer, processor, or shard files (14 visible artifacts total)

Quick start

llama.cpp

Download a .gguf file that fits your available memory, then run it with a current llama.cpp build:

llama-cli \
  -m /path/to/model.gguf \
  -p "Write a concise technical summary."

For vision or any-to-any models, download the matching multimodal projection file when one is provided and follow the source model's modality-specific instructions.

Compatibility and responsible use

  • Use a runtime that explicitly supports this format, architecture, and modality.
  • Keep configuration, tokenizer, processor, projection, and weight files from the same revision together.
  • Review the source model card and license before redistribution or deployment.
  • Hardware needs depend on parameter count, context length, cache precision, quantization, and concurrency.
  • Report reproducible issues with the runtime version, hardware, launch command, and a minimal example.

Quantization or conversion changes numerical behavior, memory use, and throughput relative to the source checkpoint; validate quality on your own workload.

Generated outputs may be inaccurate or unsuitable for a given use case. Users are responsible for testing behavior, applying appropriate safeguards, and complying with applicable licenses and laws.

All quantizations were produced using an importance matrix (imatrix) computed on 128 chunks of WikiText-2-raw-v1 for optimal quality at every bit-width.

Quantization Variants

Variant Size BPW Notes
F16 17.0 GB 16.00 Lossless half-precision
Q8_0 8.9 GB 8.50 Near-lossless, 8-bit round quant
Q6_K 6.9 GB 6.57 6-bit K-quant, excellent quality
Q5_K_M 6.1 GB 5.77 5-bit K-medium, recommended sweet spot
Q5_K_S 5.9 GB 5.62 5-bit K-small, slight size savings
Q4_K_M 5.3 GB 5.02 4-bit K-medium, best quality/size ratio
Q4_K_S 5.0 GB 4.77 4-bit K-small, good balance
IQ4_XS 4.9 GB 4.63 4-bit importance matrix, extra small
Q3_K_M 4.4 GB 4.12 3-bit K-medium
IQ3_M 4.2 GB 3.94 3-bit importance matrix, medium
Q3_K_S 4.0 GB 3.80 3-bit K-small
IQ3_XXS 3.7 GB 3.51 3-bit importance matrix, extra-extra small
Q2_K 3.6 GB 3.41 2-bit K-quant, smallest size

Recommendations

  • Best overall: Q4_K_M or Q5_K_M — excellent quality-to-size ratio
  • Maximum quality: Q6_K or Q8_0
  • Tight VRAM: IQ4_XS or Q3_K_M
  • Minimum size: Q2_K

Usage

Compatible with llama.cpp, LM Studio, Ollama, text-generation-webui, and any GGUF-compatible inference engine.

llama-cli -m Qwen3.5-9B-GLM5.1-Distill-v1-Q4_K_M.gguf -p "Hello, world!"

Source Model

Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1 — a Qwen3.5-9B variant distilled with GLM5.1.