QW

Qwen3.8 Flash Next REAM 60Pct

QwenGGUF by mradermacherUpdated 2026-08-31
Download on Hugging Face
Parameters129B
Context256K
Layers48
Architectureqwen4exp
Smallest quant0.4 GB
Quick answer

Qwen3.8 Flash Next REAM 60Pct needs about 88.3 GB of memory at Q4_K_M (a 87.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 14 quants, from 0.4 GB to 97.4 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3.8 Flash Next REAM 60Pct – a 129B parameter MoE model compressed with REAM

Qwen3.8 Flash Next REAM 60Pct is a 129 billion‑parameter model using the qwen4exp architecture. It is a 60 % compressed version of Qwen3.8‑Flash‑Next, created with Router Expert Activation Merging. The model supports a context of 262,144 tokens.

Good at

  • Large context handling
  • MoE compression
  • High‑parameter density

Limits

  • No vision support
  • License not specified
  • Experimental release

Best for

  • Long‑form text generation
  • Research prototyping
  • Memory‑constrained inference

Who it’s for. Developers and researchers needing a large‑parameter model with reduced size. The model is experimental and should be used for testing and research rather than production.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 1.7 GB
Fits Get file →
Q2_K60.8 GB 62.1 GB
Too big Get file →
Q3_K_S65.8 GB 67.1 GB
Too big Get file →
IQ3_S66.0 GB 67.3 GB
Too big Get file →
IQ3_M66.4 GB 67.7 GB
Too big Get file →
Q3_K_M69.2 GB 70.5 GB
Too big Get file →
Q3_K_L70.7 GB 72.0 GB
Too big Get file →
IQ4_XS71.3 GB 72.6 GB
Too big Get file →
Q4_073.0 GB 74.3 GB
Too big Get file →
Q4_180.8 GB 82.1 GB
Too big Get file →
Q4_K_S82.5 GB 83.8 GB
Too big Get file →
Q4_K_M87.0 GB 88.3 GB
Too big Get file →
Q5_K_S93.5 GB 94.8 GB
Too big Get file →
Q5_K_M97.4 GB 98.7 GB
Too big Get file →

For 8 GB VRAM use Q2_K (file size 60.79 GB, memory 62.1 GB at 8 k context). For 16 GB VRAM use Q3_K_S (65.84 GB, 67.1 GB). For 24 GB VRAM use Q4_0 (72.98 GB, 74.3 GB). Estimates are approximate.

What GPU do you need for Qwen3.8 Flash Next REAM 60Pct?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 the main file (0.4 GB file, about 1.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).

Which Qwen3.8 Flash Next REAM 60Pct quant should you choose?

Q4_K_M is the usual starting point for Qwen3.8 Flash Next REAM 60Pct: it balances file size and quality well. Here it is a 87.0 GB file.

If memory is tight, the smallest file is the first one in the table at 0.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen4exp
Parameters129B (approximate, mixture of experts)
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyQwen
Downloads (HF)1,782
Last updated2026-08-31

Frequently asked questions about Qwen3.8 Flash Next REAM 60Pct

How much VRAM does Qwen3.8 Flash Next REAM 60Pct need?

About 88.3 GB at Q4_K_M with an 8K context window. That is the 87.0 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 REAM 60Pct on an 8 GB GPU?

Yes, with the smaller files: the 0.4 GB file needs about 1.7 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 REAM 60Pct GGUF?

It depends on the quant: file is 0.4 GB, Q2_K is 60.8 GB, Q3_K_S is 65.8 GB, IQ3_S is 66.0 GB, IQ3_M is 66.4 GB, Q3_K_M is 69.2 GB and 8 more.

What context length does Qwen3.8 Flash Next REAM 60Pct support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Qwen3.8 Flash Next REAM 60Pct GGUF?

The files are on Hugging Face in the mradermacher/Qwen3.8-Flash-Next-REAM-60Pct-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

The smallest quant, Q2_K, requires about 62.1 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

Is the model licensed for commercial use?

The license is not specified in the provided data.

Other GGUFs of Qwen3.8-Flash-Next-REAM-60Pct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →