SkillGym Qwen3.5 122B A10B needs about 77.2 GB of memory at Q4_K_M (a 75.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 9 quants, from 45.8 GB (Q2_K) to 88.7 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
SkillGym Qwen3.5 122B A10B – a 122B parameter LLM fine‑tuned for skill‑based agent tasks
SkillGym Qwen3.5 122B A10B is a 125 billion‑parameter model with 10 billion active parameters in a mixture of experts. It is trained on SkillGym trajectories to read and apply agent skills via tool calls or shell commands. The model supports reasoning, tools, and vision.
Good at
- Reading and applying skill files
- Tool‑based task execution
- Vision‑enabled instruction following
Limits
- Large context budget can be exhausted in long episodes
- Reasoning may repeat and hit per‑turn token limits
- Not tuned for general chat use
Best for
- Skill‑based agent workflows
- Automated environment interaction
- Tool‑augmented task solving
Who it’s for. Developers building agent systems that rely on pre‑defined skill sets and tool integration. The model is ideal for environments where agents must consult skill folders and execute commands in a sandboxed workspace.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 45.8 GB | 47.1 GB | Too big | Get file → | |
| Q3_K_S | 54.0 GB | 55.3 GB | Too big | Get file → | |
| Q3_K_M | 59.8 GB | 61.1 GB | Too big | Get file → | |
| Q3_K_L | 64.7 GB | 66.0 GB | Too big | Get file → | |
| IQ4_XS | 67.6 GB | 68.9 GB | Too big | Get file → | |
| Q4_K_S | 71.1 GB | 72.4 GB | Too big | Get file → | |
| Q4_K_M | 75.8 GB | 77.2 GB | Too big | Get file → | |
| Q5_K_S | 85.9 GB | 87.3 GB | Too big | Get file → | |
| Q5_K_M | 88.7 GB | 90.0 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (45.81 GB file, 47.1 GB memory). For 12 GB VRAM use Q3_K_S (54.01 GB file, 55.3 GB memory). For 16 GB VRAM use Q4_K_S (71.08 GB file, 72.4 GB memory). Estimates are approximate.
What GPU do you need for SkillGym Qwen3.5 122B A10B?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q2_K (45.8 GB file, about 47.1 GB in use).
Which SkillGym Qwen3.5 122B A10B quant should you choose?
Q4_K_M is the usual starting point for SkillGym Qwen3.5 122B A10B: it balances file size and quality well. Here it is a 75.8 GB file.
If memory is tight, the smallest file is Q2_K at 45.8 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 SkillGym Qwen3.5 122B A10B
How much VRAM does SkillGym Qwen3.5 122B A10B need?
About 77.2 GB at Q4_K_M with an 8K context window. That is the 75.8 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 SkillGym Qwen3.5 122B A10B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 47.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SkillGym Qwen3.5 122B A10B GGUF?
It depends on the quant: Q2_K is 45.8 GB, Q3_K_S is 54.0 GB, Q3_K_M is 59.8 GB, Q3_K_L is 64.7 GB, IQ4_XS is 67.6 GB, Q4_K_S is 71.1 GB and 3 more.
What context length does SkillGym Qwen3.5 122B A10B 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 3.3 GB at 32K.
Where can I download SkillGym Qwen3.5 122B A10B GGUF?
The files are on Hugging Face in the mradermacher/SkillGym-Qwen3.5-122B-A10B-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 SkillGym Qwen3.5 122B A10B 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 SkillGym Qwen3.5 122B A10B on 8 GB VRAM?
Use the Q2_K quant; it requires about 47.1 GB of VRAM at 8 k context, which is beyond 8 GB, so it is not feasible.
Does the model support vision?
Yes, the model has detected vision ability, but it is not tuned for general vision tasks.
Is the model licensed for commercial use?
The model is released under the apache-2.0 license, which allows commercial use with attribution.