typecastlm qwen3.5 3.8b needs about 5.4 GB of memory at Q8_0 (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.0 GB (Q8_0) to 7.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
TypeCastLM Qwen3.5 3.8B – a fast, calibrated decision model
TypeCastLM Qwen3.5 3.8B is a causal language model with a vision encoder, built on the Qwen3.5 architecture. It contains 3.76B parameters and supports four Jev modes: noul, choice, scale, and tfu. The model is released under Apache‑2.0 and is available in GGUF format.
Good at
- Fast single‑pass decisions
- Calibrated output per mode
- Low‑latency inference
Limits
- Requires 5.4 GB VRAM for Q8_0 at 8 k context
- Large context length of 262,144 tokens
- No external vision support beyond the built‑in encoder
Best for
- Jev‑style decision pipelines
- Rapid inference on consumer GPUs
- Calibration‑sensitive applications
Who it’s for. Developers needing a lightweight, open‑weight model for decision tasks that require fast, calibrated responses. The model is suitable for edge deployments where memory is limited but speed is critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 4.0 GB | 5.4 GB | Fits | Get file → | |
| BF16 | 7.5 GB | 9.0 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8_0 quantized file (4.01 GB, ~5.4 GB memory at 8 k context). If more VRAM is available, BF16 (7.53 GB, ~9 GB memory) offers higher precision. The estimates are approximate.
What GPU do you need for typecastlm qwen3.5 3.8b?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (4.0 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.0 GB file, about 5.4 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (7.5 GB file, about 9.0 GB in use).
Which typecastlm qwen3.5 3.8b quant should you choose?
Q8_0 (4.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about typecastlm qwen3.5 3.8b
How much VRAM does typecastlm qwen3.5 3.8b need?
About 5.4 GB at Q8_0 with an 8K context window. That is the 4.0 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 typecastlm qwen3.5 3.8b on an 8 GB GPU?
Yes, with Q8_0: the 4.0 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of typecastlm qwen3.5 3.8b GGUF?
It depends on the quant: Q8_0 is 4.0 GB, BF16 is 7.5 GB.
What context length does typecastlm qwen3.5 3.8b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download typecastlm qwen3.5 3.8b GGUF?
The files are on Hugging Face in the mihailgribov/typecastlm-qwen3.5-3.8b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does typecastlm qwen3.5 3.8b 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?
Yes, the Q8_0 quantized version requires about 5.4 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does the model support vision tasks?
It includes a vision encoder, but the primary use is for Jev decision making; no separate vision API is provided.
What license applies?
The model is released under the Apache‑2.0 license, allowing free use and modification.