OR

Humo Coder 35B A3B

OrnithGGUF by ooptimumUpdated 2026-10-02
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant0.2 GB
Quick answer

Humo Coder 35B A3B needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 0.2 GB to 26.6 GB (Q5_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Humo Coder 35B A3B – a mixture‑of‑experts model for coding and agentic tasks

Humo Coder 35B A3B is a 35.5B parameter model built on Ornith‑1.5. It activates about 3B parameters per token and supports coding, reasoning, tool calling and vision. The model is released under the MIT license and is available in several GGUF quantizations.

Good at

  • High‑quality code generation
  • Tool‑aware agentic reasoning
  • Multimodal vision support

Limits

  • Requires large VRAM for high‑quality quants
  • No native vision support in llama.cpp
  • Limited to 262144 context tokens

Best for

  • Developers building code assistants
  • Researchers testing agentic coding benchmarks
  • Teams needing a lightweight coding model

Who it’s for. The model is intended for developers, researchers, and teams that need a powerful coding assistant with tool‑calling capabilities. It is suitable for environments that can run llama.cpp or compatible runtimes such as LM Studio, Ollama, or KoboldCpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.4 GB
Fits Get file →
IQ3_M15.8 GB 17.0 GB
Too big Get file →
Q4_K_M21.7 GB 22.9 GB
Too big Get file →
Q4_K_XL22.5 GB 23.7 GB
Too big Get file →
Q5_K_M25.3 GB 26.5 GB
Too big Get file →
Q5_K_XL26.6 GB 27.8 GB
Too big Get file →

For 8 GB VRAM, use the IQ3_M quant (file size 15.81 GB, estimated 17 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (21.71 GB, 22.9 GB memory) is a good balance. If 16 GB VRAM is available, Q5_K_XL (26.65 GB, 27.8 GB memory) provides the highest quality. Always leave extra space for KV cache.

What GPU do you need for Humo Coder 35B A3B?

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 (0.2 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_XL (22.5 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_XL (26.6 GB file, about 27.8 GB in use).

Which Humo Coder 35B A3B quant should you choose?

Q4_K_M is the usual starting point for Humo Coder 35B A3B: it balances file size and quality well. Here it is a 21.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.2 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

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized byooptimum
FamilyOrnith
Licensemit
Downloads (HF)295
Last updated2026-10-02

Frequently asked questions about Humo Coder 35B A3B

How much VRAM does Humo Coder 35B A3B need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 Humo Coder 35B A3B on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.2 GB, IQ3_M is 15.8 GB, Q4_K_M is 21.7 GB, Q4_K_XL is 22.5 GB, Q5_K_M is 25.3 GB, Q5_K_XL is 26.6 GB.

What context length does Humo Coder 35B A3B 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 Humo Coder 35B A3B GGUF?

The files are on Hugging Face in the ooptimum/Humo-Coder-35B-A3B-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 Humo Coder 35B A3B 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 Humo Coder 35B A3B on 8 GB VRAM?

Use the IQ3_M quant; it requires about 17 GB memory at 8 k context, which fits within 8 GB VRAM plus some overhead.

Does the model support vision tasks?

Yes, the model has detected vision ability, but llama.cpp does not provide native vision support; a separate vision pipeline is needed.

What license applies to this model?

The model is released under the MIT license, allowing free use and modification.

Other GGUFs of Ornith-1.5-35B-A3B

Similar models

Browse all →

More Ornith models

All Ornith →

Other large models

All large models →