QW

Qwen3.5 35B A3B Kazakh

QwenGGUF by mradermacherUpdated 2026-10-07
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant13.0 GB
Quick answer

Qwen3.5 35B A3B Kazakh needs about 22.4 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 11 quants, from 13.0 GB (Q2_K) to 37.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.5 35B A3B Kazakh – a 34.7B parameter LLM with Kazakh tokenization

Qwen3.5 35B A3B Kazakh is a 34.7B parameter model built on the Qwen architecture. It extends the tokenizer with a 16K Kazakh-token vocabulary and is continued‑pretrained on Kazakh text. The model retains the base Qwen3.5 capabilities and adds efficient Kazakh language support.

Good at

  • Kazakh language understanding
  • Instruction following
  • Large context handling

Limits

  • Vision capability detected but not supported in GGUF
  • Large memory requirement for full precision
  • No post‑training fine‑tuning

Best for

  • Chatbots in Kazakh
  • Kazakh text generation
  • Knowledge retrieval in Kazakh

Who it’s for. Developers building Kazakh language applications who need a large, instruction‑aligned model. The model is suitable for users with sufficient GPU memory to run the larger quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.0 GB 14.1 GB
Too big Get file →
Q3_K_S15.2 GB 16.4 GB
Too big Get file →
Q3_K_M16.8 GB 18.0 GB
Too big Get file →
Q3_K_L18.2 GB 19.3 GB
Too big Get file →
IQ4_XS19.0 GB 20.2 GB
Too big Get file →
Q4_K_S19.9 GB 21.1 GB
Too big Get file →
Q4_K_M21.2 GB 22.4 GB
Too big Get file →
Q5_K_S24.0 GB 25.2 GB
Too big Get file →
Q5_K_M24.8 GB 25.9 GB
Too big Get file →
Q6_K28.6 GB 29.7 GB
Too big Get file →
Q8_037.0 GB 38.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (21.21 GB file, ~22.4 GB memory at 8k context). For 12 GB VRAM, Q5_K_S (24.03 GB file, ~25.2 GB memory). For 16 GB VRAM, Q6_K (28.57 GB file, ~29.7 GB memory). Estimates are approximate.

What GPU do you need for Qwen3.5 35B A3B Kazakh?

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 Q2_K (13.0 GB file, about 14.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.6 GB file, about 29.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.0 GB file, about 38.1 GB in use).

Which Qwen3.5 35B A3B Kazakh quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 35B A3B Kazakh: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 37.0 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 Q2_K at 13.0 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
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,822
Last updated2026-10-07

Frequently asked questions about Qwen3.5 35B A3B Kazakh

How much VRAM does Qwen3.5 35B A3B Kazakh need?

About 22.4 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 Qwen3.5 35B A3B Kazakh on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5 35B A3B Kazakh GGUF?

It depends on the quant: Q2_K is 13.0 GB, Q3_K_S is 15.2 GB, Q3_K_M is 16.8 GB, Q3_K_L is 18.2 GB, IQ4_XS is 19.0 GB, Q4_K_S is 19.9 GB and 5 more.

What context length does Qwen3.5 35B A3B Kazakh 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 Qwen3.5 35B A3B Kazakh GGUF?

The files are on Hugging Face in the mradermacher/Qwen3.5-35B-A3B-Kazakh-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 Qwen3.5 35B A3B Kazakh 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 this model on 8 GB VRAM?

Use the Q4_K_M quantization; it requires about 22.4 GB memory at 8k context, which exceeds 8 GB VRAM, so it is not feasible.

Does the model support vision tasks?

The model has detected vision ability, but the GGUF version does not include vision support.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →