DE

DeepSeek V2 Lite FP8 BLOCK Fused

DeepSeekGGUF by mradermacherUpdated 2026-02-08
Download on Hugging Face
Parameters15.7B
Context160K
Layers27
Architecturedeepseek2
Smallest quant0.0 GB
Quick answer

DeepSeek V2 Lite FP8 BLOCK Fused needs about 11.3 GB of memory at Q4_K_M (a 10.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 14.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

DeepSeek V2 Lite FP8 BLOCK Fused is a 15.7B-parameter DeepSeek model in GGUF format, quantized by mradermacher. Its trained context length is 160K tokens. The repository has 25 quant files, from 0.0 GB to 14.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
IQ1_S5.0 GB 6.0 GB
Fits Get file →
IQ1_M5.2 GB 6.2 GB
Fits Get file →
IQ2_XXS5.6 GB 6.6 GB
Fits Get file →
IQ2_XS6.0 GB 7.0 GB
Fits Get file →
IQ2_S6.0 GB 7.0 GB
Fits Get file →
IQ2_M6.3 GB 7.3 GB
Tight Get file →
Q2_K6.4 GB 7.4 GB
Tight Get file →
Q2_K_S6.5 GB 7.4 GB
Tight Get file →
IQ3_XXS7.0 GB 8.0 GB
Tight Get file →
IQ3_XS7.1 GB 8.1 GB
Too big Get file →
IQ3_S7.5 GB 8.5 GB
Too big Get file →
Q3_K_S7.5 GB 8.5 GB
Too big Get file →
IQ3_M7.6 GB 8.5 GB
Too big Get file →
Q3_K_M8.1 GB 9.1 GB
Too big Get file →
Q3_K_L8.5 GB 9.4 GB
Too big Get file →
IQ4_XS8.6 GB 9.6 GB
Too big Get file →
IQ4_NL8.9 GB 9.9 GB
Too big Get file →
Q4_08.9 GB 9.9 GB
Too big Get file →
Q4_K_S9.5 GB 10.5 GB
Too big Get file →
Q4_19.9 GB 10.9 GB
Too big Get file →
Q4_K_M10.4 GB 11.3 GB
Too big Get file →
Q5_K_S11.1 GB 12.1 GB
Too big Get file →
Q5_K_M11.9 GB 12.8 GB
Too big Get file →
Q6_K14.1 GB 15.1 GB
Too big Get file →

What GPU do you need for DeepSeek V2 Lite FP8 BLOCK Fused?

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 (0.0 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ1_S (5.0 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (7.0 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (10.4 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (14.1 GB file, about 15.1 GB in use).

Which DeepSeek V2 Lite FP8 BLOCK Fused quant should you choose?

Q4_K_M is the usual starting point for DeepSeek V2 Lite FP8 BLOCK Fused: it balances file size and quality well. Here it is a 10.4 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architecturedeepseek2
Parameters15.7B (approximate, mixture of experts)
Layers27
Trained context163,840 tokens
KV cache (fp16)57 KB per token

Source

Quantized bymradermacher
FamilyDeepSeek
Licenseother
Downloads (HF)403
Last updated2026-02-08

Frequently asked questions about DeepSeek V2 Lite FP8 BLOCK Fused

How much VRAM does DeepSeek V2 Lite FP8 BLOCK Fused need?

About 11.3 GB at Q4_K_M with an 8K context window. That is the 10.4 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 DeepSeek V2 Lite FP8 BLOCK Fused on an 8 GB GPU?

Yes, with IQ3_XXS: the 7.0 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DeepSeek V2 Lite FP8 BLOCK Fused GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 5.0 GB, IQ1_M is 5.2 GB, IQ2_XXS is 5.6 GB, IQ2_XS is 6.0 GB, IQ2_S is 6.0 GB and 19 more.

What context length does DeepSeek V2 Lite FP8 BLOCK Fused support?

The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download DeepSeek V2 Lite FP8 BLOCK Fused GGUF?

The files are on Hugging Face in the mradermacher/DeepSeek-V2-Lite-FP8-BLOCK-Fused-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 DeepSeek V2 Lite FP8 BLOCK Fused use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of DeepSeek-V2-Lite-FP8-BLOCK-Fused

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →