Qwen3.5 122B A10B Claude Distill needs about 75.5 GB of memory at Q4_K_M (a 74.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.4 GB to 86.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3.5 122B A10B Claude Distill – a vision‑capable, 122B parameter model distilled from Claude
This model is a fine‑tuned version of Qwen3.5‑122B‑A10B with 122B total parameters and 10B active parameters per token. It inherits vision‑language capabilities and is trained on ~14.9K Claude reasoning traces. The model is released under the Apache‑2.0 license.
Good at
- Vision‑language tasks
- Reasoning and chain‑of‑thought generation
- Multi‑domain coverage
Limits
- Requires large VRAM for full precision
- Limited training data may affect generalization
- Not suitable for medical, legal, or financial advice without verification
Best for
- Research and educational use
- Multimodal reasoning experiments
- Testing vision‑language integration
Who it’s for. Researchers and developers looking to experiment with a large, vision‑capable LLM distilled from Claude. The model is intended for research and educational purposes and should be used responsibly.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 1.7 GB | Fits | Get file → | |
| IQ1_S | 25.3 GB | 26.6 GB | Too big | Get file → | |
| IQ1_M | 28.1 GB | 29.4 GB | Too big | Get file → | |
| IQ2_XXS | 32.6 GB | 33.9 GB | Too big | Get file → | |
| IQ2_XS | 36.3 GB | 37.6 GB | Too big | Get file → | |
| IQ2_S | 36.6 GB | 37.9 GB | Too big | Get file → | |
| IQ2_M | 40.3 GB | 41.6 GB | Too big | Get file → | |
| Q2_K_S | 42.1 GB | 43.4 GB | Too big | Get file → | |
| Q2_K | 44.9 GB | 46.2 GB | Too big | Get file → | |
| IQ3_XXS | 47.4 GB | 48.7 GB | Too big | Get file → | |
| IQ3_XS | 50.3 GB | 51.7 GB | Too big | Get file → | |
| Q3_K_S | 52.9 GB | 54.2 GB | Too big | Get file → | |
| IQ3_S | 53.1 GB | 54.4 GB | Too big | Get file → | |
| IQ3_M | 53.8 GB | 55.1 GB | Too big | Get file → | |
| Q3_K_M | 58.6 GB | 59.9 GB | Too big | Get file → | |
| Q3_K_L | 63.4 GB | 64.7 GB | Too big | Get file → | |
| IQ4_XS | 65.5 GB | 66.8 GB | Too big | Get file → | |
| Q4_0 | 69.3 GB | 70.6 GB | Too big | Get file → | |
| Q4_K_S | 69.7 GB | 71.0 GB | Too big | Get file → | |
| Q4_K_M | 74.2 GB | 75.5 GB | Too big | Get file → | |
| Q4_1 | 76.6 GB | 77.9 GB | Too big | Get file → | |
| Q5_K_S | 84.2 GB | 85.5 GB | Too big | Get file → | |
| Q5_K_M | 86.9 GB | 88.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (25.34 GB file, 26.6 GB memory at 8 k context). For 16 GB VRAM, IQ2_XS (36.26 GB file, 37.6 GB memory) or Q2_K (44.9 GB file, 46.2 GB memory). For 24 GB VRAM, Q3_K_M (58.61 GB file, 59.9 GB memory) or Q4_K_M (74.21 GB file, 75.5 GB memory). Memory estimates are approximate.
What GPU do you need for Qwen3.5 122B A10B Claude Distill?
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 (0.4 GB file, about 1.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 32 GB VRAM: the best quant that fits is IQ1_M (28.1 GB file, about 29.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q2_K (44.9 GB file, about 46.2 GB in use).
Which Qwen3.5 122B A10B Claude Distill quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 122B A10B Claude Distill: it balances file size and quality well. Here it is a 74.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.4 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 Qwen3.5 122B A10B Claude Distill
How much VRAM does Qwen3.5 122B A10B Claude Distill need?
About 75.5 GB at Q4_K_M with an 8K context window. That is the 74.2 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 122B A10B Claude Distill on an 8 GB GPU?
Yes, with the smaller files: the 0.4 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 122B A10B Claude Distill GGUF?
It depends on the quant: file is 0.4 GB, IQ1_S is 25.3 GB, IQ1_M is 28.1 GB, IQ2_XXS is 32.6 GB, IQ2_XS is 36.3 GB, IQ2_S is 36.6 GB and 17 more.
What context length does Qwen3.5 122B A10B Claude Distill support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Qwen3.5 122B A10B Claude Distill GGUF?
The files are on Hugging Face in the mradermacher/Qwen3.5-122B-A10B-Claude-distill-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 Qwen3.5 122B A10B Claude Distill 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 IQ1_S quant, which requires about 26.6 GB of VRAM at 8 k context.
Does this model support vision tasks?
Yes, it inherits vision‑language capabilities from Qwen3.5.
What license does it use?
The model is released under the Apache‑2.0 license.