TE

Tals coder flash 02

TernaryGGUF by talxccUpdated 2026-10-01
Download on Hugging Face
Parameters28.9B
Context256K
Layers—
Architectureqwen35
Smallest quant8.3 GB
Quick answer

Tals coder flash 02 needs about 9.7 GB of memory at its main file (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Tals coder flash 02 – 28.9B ternary Qwen3.5 model with fast coding performance

Tals coder flash 02 is a 28.9B ternary Qwen3.5 model optimized for coding. It delivers high token generation speeds on consumer GPUs and supports a 262144‑token context. The model is released under the Apache‑2.0 license.

Good at

  • Fast token generation on 16GB GPUs
  • Large context length
  • Coding tasks

Limits

  • No built‑in vision; separate projector required
  • Requires 8.25 GB GGUF file
  • Memory estimate 9.7 GB at 8k context

Best for

  • Rapid code generation
  • On‑device coding assistants
  • Large‑context code analysis

Who it’s for. Developers and researchers needing a fast, large‑context coding model that runs on consumer GPUs. The model is suitable for local inference with llama.cpp or compatible runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.3 GB 9.7 GB
Too big Get file →

The only available quant is the 8.25 GB GGUF file. It requires approximately 9.7 GB of RAM at 8k context. For systems with 8 GB VRAM, the model will not fit; a larger GPU or reduced context is needed.

What GPU do you need for Tals coder flash 02?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (8.3 GB file, about 9.7 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters28.9B
Trained context262,144 tokens

Source

Quantized bytalxcc
FamilyTernary
Licenseapache-2.0
Downloads (HF)315
Last updated2026-10-01

Frequently asked questions about Tals coder flash 02

How much VRAM does Tals coder flash 02 need?

About 9.7 GB at its main file with an 8K context window. That is the 8.3 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 Tals coder flash 02 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Tals coder flash 02 GGUF?

It depends on the quant: file is 8.3 GB.

What context length does Tals coder flash 02 support?

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

Where can I download Tals coder flash 02 GGUF?

The files are on Hugging Face in the talxcc/Tals-coder-flash-02 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Tals coder flash 02 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.

Does the model support vision tasks?

Vision support is provided by a separate 0.63 GB CLIP Q8_0 projector; the main model does not include vision weights.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Ternary-Bonsai-2-27B-gguf

Similar models

Browse all →

More from talxcc

All by talxcc →

More Ternary models

All Ternary →

Other medium models

All medium models →