QW

Qwen3.8 Flash Next GSQ RCO abliterated

QwenGGUF by SC117Updated 2026-10-24
Download on Hugging Face
Parameters177B
Context256K
Layers—
Architectureqwen4exp-mtp
Smallest quant0.9 GB
Quick answer

Qwen3.8 Flash Next GSQ RCO abliterated needs about 75.3 GB of memory at Q2_0 (a 66.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 0.9 GB (Q2_0) to 83.9 GB (IQ3_S).

Qwen3.8 Flash Next GSQ RCO abliterated – a 177B sparse MoE model in GGUF format

Qwen3.8 Flash Next GSQ RCO abliterated is a 177‑billion‑parameter sparse mixture‑of‑experts model. It uses GSQ‑RCO non‑uniform quantization and includes a vision projector for multimodal use. The model ships as two shards and runs unmodified in llama.cpp, Ollama, and LM Studio.

Good at

  • Large‑scale text generation
  • Multimodal inference with vision projector
  • Sparse MoE efficiency

Limits

  • No built‑in guardrails – safety mitigations removed
  • Requires 8‑k context for memory estimates
  • Large memory footprint for higher‑bit quantizations

Best for

  • Research on sparse MoE architectures
  • Deploying multimodal inference on local GPUs
  • Benchmarking non‑uniform quantization methods

Who it’s for. Researchers and developers needing a high‑parameter sparse MoE model with vision capabilities. The abliterated build is suitable for environments where safety guardrails are managed separately.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_00.9 GB 1.5 GB
Fits Get file →
Q4_02.2 GB 3.0 GB
Fits Get file →
Q8_04.1 GB 5.1 GB
Fits Get file →
Q2_066.8 GB (2 parts) 75.3 GB
Too big Get file →
IQ2_XS68.5 GB (2 parts) 77.2 GB
Too big Get file →
IQ3_XXS76.1 GB (2 parts) 85.8 GB
Too big Get file →
IQ3_S83.9 GB (2 parts) 94.4 GB
Too big Get file →

For 8‑GB VRAM use the Q2_0 quantization (0.89 GB file, ~1.5 GB RAM). For 16‑GB VRAM use Q8_0 (4.14 GB file, ~5.1 GB RAM). Larger budgets can use the 66.82 GB Q2_0 shard or the 68.47 GB IQ2_XS shard, with memory estimates of 75.3 GB and 77.2 GB respectively.

What GPU do you need for Qwen3.8 Flash Next GSQ RCO abliterated?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q4_0 (2.2 GB file, about 3.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).

Which Qwen3.8 Flash Next GSQ RCO abliterated quant should you choose?

Q2_0 (66.8 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

If memory is tight, the smallest file is Q2_0 at 0.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen4exp-mtp
Parameters177B
Trained context262,144 tokens

Source

Quantized bySC117
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,921,615
Last updated2026-10-24

Frequently asked questions about Qwen3.8 Flash Next GSQ RCO abliterated

How much VRAM does Qwen3.8 Flash Next GSQ RCO abliterated need?

About 75.3 GB at Q2_0 with an 8K context window. That is the 66.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen3.8 Flash Next GSQ RCO abliterated on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.8 Flash Next GSQ RCO abliterated GGUF?

It depends on the quant: Q2_0 is 0.9 GB, Q4_0 is 2.2 GB, Q8_0 is 4.1 GB, Q2_0 is 66.8 GB, IQ2_XS is 68.5 GB, IQ3_XXS is 76.1 GB and 1 more.

What context length does Qwen3.8 Flash Next GSQ RCO abliterated support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download Qwen3.8 Flash Next GSQ RCO abliterated GGUF?

The files are on Hugging Face in the SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3.8 Flash Next GSQ RCO abliterated use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q2_0 quantization file is 0.89 GB and requires about 1.5 GB of RAM at 8‑k context.

Does this model support vision tasks?

Yes, it includes a vision projector (mmproj) at BF16 for multimodal use.

Is there a safety guardrail in this build?

No, the abliterated build removes built‑in refusal mechanisms; deploy it only where external safety is provided.

Other GGUFs of Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Similar models

Browse all →

More from SC117

All by SC117 →

More Qwen models

All Qwen →

Other large models

All large models →