OR

Tiel Coder 35B A3B GGUF MTP

OrnithGGUF by peculiar-ragdollUpdated 2026-10-25
Download on Hugging Face
Parameters447M
Context256K
Layers41
Architectureqwen35moe
Smallest quant12.7 GB
Quick answer

Tiel Coder 35B A3B GGUF MTP needs about 22.5 GB of memory at Q4_K_S (a 21.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 12.7 GB (Q2_K_XL) to 38.8 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Tiel Coder 35B A3B GGUF MTP – a 35B mixture‑of‑experts coder model

Tiel Coder 35B A3B is a 35B parameter mixture‑of‑experts model based on Qwen35moe. It supports coding and vision tasks and is released under the MIT license. The model was re‑quantized by peculiar‑ragdoll and is available in multiple GGUF quantizations.

Good at

  • Coding
  • Vision
  • Multi‑turn conversation

Limits

  • No vision support on all‑GPU inference
  • Requires large VRAM for higher quantizations
  • No explicit language support listed

Best for

  • Local code generation
  • Debugging codebases
  • Multi‑turn coding assistance

Who it’s for. Developers and researchers needing a local, open‑source coding model with vision capabilities. The model is suitable for users with sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_XL12.7 GB 13.9 GB
Too big Get file →
IQ3_XXS13.6 GB 14.8 GB
Too big Get file →
IQ3_S14.1 GB 15.3 GB
Too big Get file →
Q3_K_XL17.2 GB 18.4 GB
Too big Get file →
IQ4_XS18.1 GB 19.3 GB
Too big Get file →
Q4_K_S21.3 GB 22.5 GB
Too big Get file →
Q4_K_XL22.7 GB 23.9 GB
Too big Get file →
Q5_K_S25.3 GB 26.5 GB
Too big Get file →
Q5_K_XL27.0 GB 28.2 GB
Too big Get file →
Q6_K_XL32.2 GB 33.4 GB
Too big Get file →
Q8_K_XL38.8 GB 40.0 GB
Too big Get file →

For 8 GB VRAM, use Q2_K_XL (12.68 GB file, 13.9 GB memory at 8k context). For 16 GB VRAM, Q4_K_S (21.28 GB file, 22.5 GB memory) is a good balance. For 24 GB VRAM, Q5_K_XL (26.98 GB file, 28.2 GB memory) provides higher quality.

What GPU do you need for Tiel Coder 35B A3B GGUF MTP?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ3_S (14.1 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_XL (22.7 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_XL (27.0 GB file, about 28.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K_XL (38.8 GB file, about 40.0 GB in use).

Which Tiel Coder 35B A3B GGUF MTP quant should you choose?

Q4_K_S (21.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K_XL at 12.7 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

Architectureqwen35moe
Parameters447M (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized bypeculiar-ragdoll
FamilyOrnith
Licensemit
Downloads (HF)2,724,409
Last updated2026-10-25

Frequently asked questions about Tiel Coder 35B A3B GGUF MTP

How much VRAM does Tiel Coder 35B A3B GGUF MTP need?

About 22.5 GB at Q4_K_S with an 8K context window. That is the 21.3 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 Tiel Coder 35B A3B GGUF MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Tiel Coder 35B A3B GGUF MTP GGUF?

It depends on the quant: Q2_K_XL is 12.7 GB, IQ3_XXS is 13.6 GB, IQ3_S is 14.1 GB, Q3_K_XL is 17.2 GB, IQ4_XS is 18.1 GB, Q4_K_S is 21.3 GB and 5 more.

What context length does Tiel Coder 35B A3B GGUF MTP support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.

Where can I download Tiel Coder 35B A3B GGUF MTP GGUF?

The files are on Hugging Face in the peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Tiel Coder 35B A3B GGUF MTP use?

Hugging Face lists the license as mit. 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 Tiel Coder 35B A3B on 8 GB VRAM?

Use the Q2_K_XL quantization, which requires 13.9 GB memory at 8k context. It will not fit in 8 GB VRAM without swapping.

Does this model support vision tasks?

Yes, the model has detected vision ability, but it is not supported on all‑GPU inference setups.

What license does Tiel Coder 35B A3B use?

The model is released under the MIT license.

Other GGUFs of Ornith-1.5-35B-A3B

Similar models

Browse all →

More from peculiar-ragdoll

All by peculiar-ragdoll →

More Ornith models

All Ornith →

Other tiny models

All tiny models →