Noema 1.5 4B Deep needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.7 GB (Q4_K_M) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Noema 1.5 4B Deep – accuracy‑first Qwen3.5‑4B based model
Noema 1.5 4B Deep is an accuracy‑first model built from Qwen3.5‑4B. It excels at reasoning and tool use, delivering correct answers with fewer tokens. The model supports a 262,144‑token context and is text‑only.
Good at
- Reasoning
- Tool use
- Hard math and code
Limits
- No vision support
- No open‑source license
- Large 262,144‑token context
Best for
- Hard mathematics problems
- Code debugging
- Long‑form reasoning tasks
Who it’s for. Users who need a local LLM that prioritizes accuracy over speed. Ideal for developers and researchers running the model on local hardware with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 5.0 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (2.71 GB file, ~4.3 GB RAM). For 10 GB VRAM use Q5_K_M (3.07 GB file, ~4.6 GB RAM). Larger models like Q6_K or Q8_0 require more memory and are suitable for higher‑end GPUs.
What GPU do you need for Noema 1.5 4B Deep?
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 Q6_K (3.5 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which Noema 1.5 4B Deep quant should you choose?
Q4_K_M is the usual starting point for Noema 1.5 4B Deep: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 4.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Noema 1.5 4B Deep
How much VRAM does Noema 1.5 4B Deep need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Noema 1.5 4B Deep on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Noema 1.5 4B Deep GGUF?
It depends on the quant: Q4_K_M is 2.7 GB, Q5_K_M is 3.1 GB, Q6_K is 3.5 GB, Q8_0 is 4.5 GB, BF16 is 8.4 GB.
What context length does Noema 1.5 4B Deep support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Noema 1.5 4B Deep GGUF?
The files are on Hugging Face in the NoemaAI-labs/Noema-1.5-4B-Deep-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 Noema 1.5 4B Deep on 8 GB VRAM?
Yes, the Q4_K_M quantization fits in 8 GB VRAM with an estimated 4.3 GB RAM usage.
Does this model support vision?
No, it is a text‑only model with no vision capabilities.
Is the model open‑source?
No, it is an open‑weight release without an open‑source license.