QW

ThinCtx Qwen3.5 0.8B

QwenGGUF by mradermacherUpdated 2026-10-13
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.0 GB
Quick answer

ThinCtx Qwen3.5 0.8B needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 0.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

ThinCtx Qwen3.5 0.8B – small‑context LLM with 0.8B parameters

ThinCtx Qwen3.5 0.8B is a 0.752 billion‑parameter model that keeps GPU memory small by storing most context in system RAM. It uses the Qwen‑35 architecture and supports 262144‑token context. The model is available in multiple GGUF quantizations.

Good at

  • Low‑memory inference
  • Long context handling
  • Chat with Qwen3.5 template

Limits

  • Requires thinctx runtime 0.2.0+
  • No vision or tool‑calling support
  • Linux/WSL2 only

Best for

  • Running on 4 GB VRAM systems
  • Developing lightweight chatbots
  • Testing Qwen3.5 behavior

Who it’s for. Developers needing a compact Qwen3.5 variant for local deployment. Suitable for Linux or Windows 10/11 via WSL2 with NVIDIA GPU. Not recommended for tool‑calling or agents.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_S0.3 GB 1.2 GB
Fits Get file →
IQ1_M0.3 GB 1.2 GB
Fits Get file →
IQ2_XXS0.4 GB 1.3 GB
Fits Get file →
IQ2_XS0.4 GB 1.3 GB
Fits Get file →
IQ2_S0.4 GB 1.3 GB
Fits Get file →
IQ2_M0.4 GB 1.3 GB
Fits Get file →
IQ3_XXS0.4 GB 1.3 GB
Fits Get file →
Q2_K_S0.4 GB 1.3 GB
Fits Get file →
Q2_K0.4 GB 1.3 GB
Fits Get file →
Q3_K_S0.4 GB 1.3 GB
Fits Get file →
IQ3_XS0.4 GB 1.3 GB
Fits Get file →
IQ3_S0.5 GB 1.4 GB
Fits Get file →
IQ3_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_L0.5 GB 1.4 GB
Fits Get file →
Q4_00.5 GB 1.4 GB
Fits Get file →
IQ4_XS0.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
IQ4_NL0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q4_10.5 GB 1.4 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →

For 4 GB VRAM, use Q4_K_S (0.51 GB file, ~1.4 GB memory at 8k context). For 8 GB VRAM, Q5_K_M (0.58 GB file, ~1.5 GB memory) offers higher quality. For 2 GB VRAM, IQ1_S (0.33 GB file, ~1.2 GB memory) is the smallest viable option. Estimates are approximate.

What GPU do you need for ThinCtx Qwen3.5 0.8B?

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 Q6_K (0.6 GB file, about 1.5 GB in use).

Which ThinCtx Qwen3.5 0.8B quant should you choose?

Q4_K_M is the usual starting point for ThinCtx Qwen3.5 0.8B: it balances file size and quality well. Here it is a 0.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)3,218
Last updated2026-10-13

Frequently asked questions about ThinCtx Qwen3.5 0.8B

How much VRAM does ThinCtx Qwen3.5 0.8B need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 ThinCtx Qwen3.5 0.8B on an 8 GB GPU?

Yes, with Q6_K: the 0.6 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ThinCtx Qwen3.5 0.8B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB and 19 more.

What context length does ThinCtx Qwen3.5 0.8B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download ThinCtx Qwen3.5 0.8B GGUF?

The files are on Hugging Face in the mradermacher/ThinCtx-Qwen3.5-0.8B-i1-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 ThinCtx Qwen3.5 0.8B use?

Hugging Face lists the license as other. 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 ThinCtx Qwen3.5 0.8B on 4 GB VRAM?

Yes, with the Q4_K_S quantization the model uses about 1.4 GB GPU memory at 8k context, fitting within 4 GB VRAM.

Does ThinCtx support vision or tool calling?

No. The conversion loses most function‑calling capability and has no vision support.

What runtime is required to run this model?

ThinCtx models require the thinctx runtime, version 0.2.0 or newer, with 1.0.1 recommended for shared memory and WSL2 support.

Other GGUFs of ThinCtx-Qwen3.5-0.8B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other tiny models

All tiny models →