Swift 1.5 Qwen3.8 27b Heretic needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 15 quants, from 0.0 GB to 22.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Swift 1.5 Qwen3.8 27b Heretic – a vision‑enabled, 27B parameter Qwen model
Swift 1.5 Qwen3.8 27b Heretic is a 27‑billion‑parameter Qwen model with vision capabilities. It is an ablated build that removes safety alignment but retains the vision tower and other core components. The model is available in multiple GGUF quantizations.
Good at
- Vision tasks with large context
- Reasoning with 262,144 token context
- Research‑grade ablation for safety studies
Limits
- No safety alignment – use with caution
- Requires large VRAM for higher‑bit quants
- Vision support only, no text‑only optimizations
Best for
- Vision‑enabled research prototypes
- Large‑context reasoning experiments
- Testing ablation effects on refusal metrics
Who it’s for. Researchers and developers who need a vision‑capable Qwen model for experimentation. The model is a research artifact; it lacks safety alignment and should be used responsibly.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| Q2_K | 10.9 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_S | 12.3 GB | 14.9 GB | Too big | Get file → | |
| IQ3_S | 12.6 GB | 15.3 GB | Too big | Get file → | |
| IQ3_M | 12.8 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_L | 14.6 GB | 17.2 GB | Too big | Get file → | |
| IQ4_XS | 15.3 GB | 18.0 GB | Too big | Get file → | |
| Q4_0 | 15.8 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_S | 15.8 GB | 18.5 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q4_1 | 17.3 GB | 20.0 GB | Too big | Get file → | |
| Q5_K_S | 19.0 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 22.2 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (10.86 GB file, ~13.5 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (16.81 GB file, ~19.5 GB memory) or Q5_K_S (18.97 GB file, ~21.7 GB memory). Higher‑bit quants require more than 24 GB VRAM.
What GPU do you need for Swift 1.5 Qwen3.8 27b Heretic?
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 (0.0 GB file, about 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (12.8 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.4 GB file, about 25.1 GB in use).
Which Swift 1.5 Qwen3.8 27b Heretic quant should you choose?
Q4_K_M is the usual starting point for Swift 1.5 Qwen3.8 27b Heretic: it balances file size and quality well. Here it is a 16.8 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
Source
Frequently asked questions about Swift 1.5 Qwen3.8 27b Heretic
How much VRAM does Swift 1.5 Qwen3.8 27b Heretic need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Swift 1.5 Qwen3.8 27b Heretic on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Swift 1.5 Qwen3.8 27b Heretic GGUF?
It depends on the quant: file is 0.0 GB, Q2_K is 10.9 GB, Q3_K_S is 12.3 GB, IQ3_S is 12.6 GB, IQ3_M is 12.8 GB, Q3_K_M is 13.5 GB and 9 more.
What context length does Swift 1.5 Qwen3.8 27b Heretic 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 Swift 1.5 Qwen3.8 27b Heretic GGUF?
The files are on Hugging Face in the mradermacher/Swift-1.5-Qwen3.8-27b-heretic-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 Swift 1.5 Qwen3.8 27b Heretic 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 Swift 1.5 Qwen3.8 27b Heretic on 8 GB VRAM?
Use the Q2_K quant; it fits within 8 GB VRAM and uses about 13.5 GB of memory at 8k context.
Does this model support vision?
Yes, the vision tower is retained in all builds, enabling image processing.
Is there safety alignment in this model?
No, safety alignment has been deliberately removed; use responsibly.