DE

deeseek r1 1.5b ft 1 q4 k m

DeeseekGGUF by maharshpatelxUpdated 2025-02-13
Download on Hugging Face
Parameters1.78B
Context128K
Layers28
Architectureqwen2
Smallest quant1.1 GB
Quick answer

deeseek r1 1.5b ft 1 q4 k m needs about 1.9 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

1.78B Qwen2 model fine‑tuned for reasoning and tool use

deeseek r1 1.5b ft 1 q4 k m is a 1.78B parameter Qwen2 model. It was fine‑tuned from unsloth/deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit and supports reasoning and tool usage. The model is released under the apache-2.0 license.

Good at

  • Reasoning
  • Tool usage
  • Qwen2 architecture

Limits

  • No vision support
  • Requires 1.9 GB VRAM at 8k context
  • License is apache-2.0

Best for

  • Chatbot development
  • Tool‑integrated assistants
  • Lightweight inference

Who it’s for. Developers building conversational agents that need reasoning and tool integration. The model is suitable for projects that can run on modest GPU memory and require an open‑source license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.1 GB 1.9 GB
Fits Get file →

The Q4_K_M quantization file is 1.12 GB. It needs about 1.9 GB VRAM at 8k context, which is suitable for 8 GB VRAM GPUs. For lower memory budgets, a different quantization would be required, but it is not available in the file list.

What GPU do you need for deeseek r1 1.5b ft 1 q4 k m?

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 Q4_K_M (1.1 GB file, about 1.9 GB in use).

Which deeseek r1 1.5b ft 1 q4 k m quant should you choose?

Q4_K_M is the usual starting point for deeseek r1 1.5b ft 1 q4 k m: it balances file size and quality well. Here it is a 1.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.78B
Layers28
Trained context131,072 tokens
KV cache (fp16)28 KB per token

Source

Quantized bymaharshpatelx
FamilyDeeseek
Licenseapache-2.0
Downloads (HF)1,028
Last updated2025-02-13

Frequently asked questions about deeseek r1 1.5b ft 1 q4 k m

How much VRAM does deeseek r1 1.5b ft 1 q4 k m need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.1 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 deeseek r1 1.5b ft 1 q4 k m on an 8 GB GPU?

Yes, with Q4_K_M: the 1.1 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of deeseek r1 1.5b ft 1 q4 k m GGUF?

It depends on the quant: Q4_K_M is 1.1 GB.

What context length does deeseek r1 1.5b ft 1 q4 k m support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download deeseek r1 1.5b ft 1 q4 k m GGUF?

The files are on Hugging Face in the maharshpatelx/deeseek-r1-1.5b-ft-1_q4_k_m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does deeseek r1 1.5b ft 1 q4 k m 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 Q4_K_M quantization requires about 1.9 GB VRAM at 8k context, which fits on an 8 GB GPU.

Does this model support vision?

No, the model does not have vision capabilities.

What license does the model use?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from maharshpatelx

All by maharshpatelx →

More Deeseek models

All Deeseek →

Other tiny models

All tiny models →