QW

Tessera 125B MoE

QwenGGUF by VoidstackloopUpdated 2026-10-27
Download on Hugging Face
Parameters162B
Context256K
Layers49
Architectureqwen4exp
Smallest quant2.9 GB
Quick answer

Tessera 125B MoE needs about 4.2 GB of memory at its main file (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.9 GB to 75.7 GB (IQ2_S). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.

Tessera 125B MoE – a large, expert‑pruned Qwen4exp model

Tessera 125B MoE is a 162‑billion‑parameter mixture of experts based on Qwen3.8‑Flash‑Next. It offers 262144‑token context and is optimized for reasoning and tool use. The model is available in two GGUF quantizations.

Good at

  • Long‑context reasoning
  • Tool integration
  • Expert routing

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License is other

Best for

  • Research on expert‑pruned LLMs
  • Long‑form content generation
  • Tool‑enabled agents

Who it’s for. Researchers and developers needing a large‑scale, expert‑pruned Qwen4exp model with extended context. The model is suitable for experimentation with routing and tool use but not for vision tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.9 GB 4.2 GB
Fits Get file →
IQ2_S75.7 GB 77.0 GB
Too big Get file →

For systems with limited memory, use the 2.89 GB GGUF (unknown quant) which needs about 4.2 GB at 8 k context. For higher performance and larger memory budgets, the 75.69 GB IQ2_S GGUF requires roughly 77 GB at 8 k context. Estimates are approximate.

What GPU do you need for Tessera 125B MoE?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is the main file (2.9 GB file, about 4.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (2.9 GB file, about 4.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (2.9 GB file, about 4.2 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (2.9 GB file, about 4.2 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (2.9 GB file, about 4.2 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (2.9 GB file, about 4.2 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (2.9 GB file, about 4.2 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen4exp
Parameters162B (approximate, mixture of experts)
Layers49
Trained context262,144 tokens
KV cache (fp16)98 KB per token

Source

Quantized byVoidstackloop
FamilyQwen
Licenseother
Downloads (HF)771
Last updated2026-10-27

Frequently asked questions about Tessera 125B MoE

How much VRAM does Tessera 125B MoE need?

About 4.2 GB at its main file with an 8K context window. That is the 2.9 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 Tessera 125B MoE on an 8 GB GPU?

Yes, with the smaller files: the 2.9 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tessera 125B MoE GGUF?

It depends on the quant: file is 2.9 GB, IQ2_S is 75.7 GB.

What context length does Tessera 125B MoE 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 3.3 GB at 32K.

Where can I download Tessera 125B MoE GGUF?

The files are on Hugging Face in the Voidstackloop/Tessera-125B-MoE repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Tessera 125B MoE use?

Hugging Face lists the license as other. 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 Tessera 125B MoE on 8 GB VRAM?

The 2.89 GB GGUF needs about 4.2 GB at 8 k context, so 8 GB VRAM is sufficient for inference with this quantization.

Does Tessera 125B MoE support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of Qwen3.8-Flash-Next

Similar models

Browse all →

More from Voidstackloop

All by Voidstackloop →

More Qwen models

All Qwen →

Other large models

All large models →