Suri Qwen 3.8 27B Companion needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 7.4 GB (IQ1_S) to 32.0 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Suri Qwen 3.8 27B Companion – a 27B vision‑enabled GGUF model
Suri Qwen 3.8 27B Companion is a 27‑billion‑parameter model based on the Qwen3.8 architecture. It supports vision tasks and is available in multiple quantizations. The model is released by Space Time and can be run with llama.cpp.
Good at
- Vision‑enabled text generation
- Large context handling
- Uncensored responses
Limits
- No license restrictions provided
- Requires significant VRAM for higher quants
- No explicit language support listed
Best for
- Chatting with image prompts
- Long‑form content creation
- Rapid prototyping of vision applications
Who it’s for. Developers and researchers needing a large, vision‑capable LLM for local inference. The model is suitable for those who can manage the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 7.4 GB | 10.1 GB | Too big | Get file → | |
| IQ1_M | 7.9 GB | 10.6 GB | Too big | Get file → | |
| IQ2_XXS | 8.7 GB | 11.4 GB | Too big | Get file → | |
| IQ2_XS | 9.3 GB | 12.0 GB | Too big | Get file → | |
| IQ2_S | 9.6 GB | 12.3 GB | Too big | Get file → | |
| Q2_K_XL | 9.9 GB | 12.6 GB | Too big | Get file → | |
| IQ2_M | 10.2 GB | 12.9 GB | Too big | Get file → | |
| IQ3_XXS | 11.4 GB | 14.1 GB | Too big | Get file → | |
| IQ3_S | 12.7 GB | 15.3 GB | Too big | Get file → | |
| IQ3_M | 12.8 GB | 15.5 GB | Too big | Get file → | |
| Q3_K_XL | 13.2 GB | 15.9 GB | Too big | Get file → | |
| IQ4_XS | 15.3 GB | 18.0 GB | Too big | Get file → | |
| Q4_K_S | 15.4 GB | 18.1 GB | Too big | Get file → | |
| IQ4_NL | 16.0 GB | 18.7 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 19.2 GB | Too big | Get file → | |
| Q4_K_XL | 17.6 GB | 20.3 GB | Too big | Get file → | |
| Q5_K_S | 18.7 GB | 21.4 GB | Too big | Get file → | |
| Q5_K_M | 19.8 GB | 22.5 GB | Too big | Get file → | |
| Q5_K_XL | 21.0 GB | 23.7 GB | Too big | Get file → | |
| Q6_K | 22.1 GB | 24.8 GB | Too big | Get file → | |
| Q6_K_M | 23.1 GB | 25.8 GB | Too big | Get file → | |
| Q6_K_L | 24.2 GB | 26.9 GB | Too big | Get file → | |
| Q6_K_XL | 25.3 GB | 28.0 GB | Too big | Get file → | |
| Q8_K_L | 28.1 GB | 30.7 GB | Too big | Get file → | |
| Q8_K_XL | 32.0 GB | 34.6 GB | Too big | Get file → |
For 8‑GB VRAM use IQ1_S or IQ1_M (file size ~7.4–7.9 GB, memory ~10–10.6 GB). For 12‑GB VRAM use IQ2_S or Q2_K_XL (file size ~9.6–9.9 GB, memory ~12–12.6 GB). For 16‑GB VRAM use Q4_K_S or Q4_K_M (file size ~15.5–16.5 GB, memory ~18–19 GB).
What GPU do you need for Suri Qwen 3.8 27B Companion?
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: the best quant that fits is IQ2_XS (9.3 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_XL (13.2 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_XL (21.0 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_K_L (28.1 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (32.0 GB file, about 34.6 GB in use).
Which Suri Qwen 3.8 27B Companion quant should you choose?
Q4_K_M is the usual starting point for Suri Qwen 3.8 27B Companion: it balances file size and quality well. Here it is a 16.5 GB file.
If memory is tight, the smallest file is IQ1_S at 7.4 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
Source
Frequently asked questions about Suri Qwen 3.8 27B Companion
How much VRAM does Suri Qwen 3.8 27B Companion need?
About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Suri Qwen 3.8 27B Companion on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Suri Qwen 3.8 27B Companion GGUF?
It depends on the quant: IQ1_S is 7.4 GB, IQ1_M is 7.9 GB, IQ2_XXS is 8.7 GB, IQ2_XS is 9.3 GB, IQ2_S is 9.6 GB, Q2_K_XL is 9.9 GB and 19 more.
What context length does Suri Qwen 3.8 27B Companion support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Suri Qwen 3.8 27B Companion GGUF?
The files are on Hugging Face in the SpaceTimee/Suri-Qwen-3.8-27B-Companion-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Suri Qwen 3.8 27B Companion on 8 GB VRAM?
Use the IQ1_S or IQ1_M quant, which require about 10–10.6 GB of VRAM at 8K context.
Does the model support image input?
Yes, the model has vision capability as indicated by its detected abilities.
What temperature range is recommended?
Set temperature between 0.8 and 1.0 for best results.