QW

SIQ 1 35B

QwenGGUF by AlexWortegaUpdated 2026-06-24
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant1.7 GB
Quick answer

SIQ 1 35B needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 1.7 GB (F16) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

SIQ 1 35B – a 35B MoE model with only ~3B active parameters

SIQ 1 35B is a causal language model built on Qwen3.6-35B-A3B. It contains 34.7B parameters, with 3B active per token. The model supports a native context length of 262,144 tokens and can be extended up to 1,010,000 tokens.

Good at

  • Agentic coding and frontend workflows
  • Reasoning with retained context
  • Autoresearch and tool‑use

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is apache‑2.0

Best for

  • Developing autonomous ML research agents
  • Writing and debugging code
  • Building agentic workflows

Who it’s for. Developers and researchers who need a lightweight MoE model for agentic tasks. The model is suitable for environments with limited GPU memory but sufficient VRAM for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.7 GB 2.9 GB
Fits Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q6_K30.2 GB 31.4 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 21.17 GB, memory 22.3 GB at 8 k context). For 16 GB VRAM, Q5_K_M (24.73 GB, 25.9 GB). For 32 GB VRAM, Q6_K (30.2 GB, 31.4 GB). The F16 quant is the largest and requires the most memory.

What GPU do you need for SIQ 1 35B?

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 F16 (1.7 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (1.7 GB file, about 2.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (1.7 GB file, about 2.9 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (1.7 GB file, about 2.9 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (1.7 GB file, about 2.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (30.2 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).

Which SIQ 1 35B quant should you choose?

Q4_K_M is the usual starting point for SIQ 1 35B: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 36.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is F16 at 1.7 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized byAlexWortega
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,264
Last updated2026-06-24

Frequently asked questions about SIQ 1 35B

How much VRAM does SIQ 1 35B need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 SIQ 1 35B on an 8 GB GPU?

Yes, with F16: the 1.7 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SIQ 1 35B GGUF?

It depends on the quant: F16 is 1.7 GB, Q4_K_M is 21.2 GB, Q5_K_M is 24.7 GB, Q6_K is 30.2 GB, Q8_0 is 36.9 GB.

What context length does SIQ 1 35B 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 2.7 GB at 32K.

Where can I download SIQ 1 35B GGUF?

The files are on Hugging Face in the AlexWortega/SIQ-1-35B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SIQ 1 35B 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.

Can I run SIQ 1 35B on 8 GB VRAM?

Use the Q4_K_M quantization; it requires about 22.3 GB memory at 8 k context, which exceeds 8 GB VRAM, so it is not feasible.

Does SIQ 1 35B support vision?

No, the model is a language model only; it has no vision encoder.

What license applies to SIQ 1 35B?

The model is released under the apache‑2.0 license.

Other GGUFs of Qwen3.6-35B-A3B

Similar models

Browse all →

More from AlexWortega

All by AlexWortega →

More Qwen models

All Qwen →

Other large models

All large models →