DE

DeepSeek Prover V2 7B

DeepSeekGGUF by mradermacherUpdated 2025-12-24
Download on Hugging Face
Parameters6.91B
Context64K
Layers30
Architecturellama
Smallest quant0.0 GB
Quick answer

DeepSeek Prover V2 7B needs about 8.7 GB of memory at Q4_K_M (a 4.2 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 5.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 16.1 GB.

DeepSeek Prover V2 7B is a 6.91B-parameter DeepSeek model in GGUF format, quantized by mradermacher. Its trained context length is 64K tokens. The repository has 25 quant files, from 0.0 GB to 5.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 4.5 GB
Fits Get file →
IQ1_S1.7 GB 6.3 GB
Fits Get file →
IQ1_M1.8 GB 6.4 GB
Fits Get file →
IQ2_XXS2.0 GB 6.6 GB
Fits Get file →
IQ2_XS2.2 GB 6.7 GB
Fits Get file →
IQ2_S2.4 GB 6.9 GB
Fits Get file →
Q2_K_S2.5 GB 7.0 GB
Fits Get file →
IQ2_M2.5 GB 7.1 GB
Fits Get file →
Q2_K2.7 GB 7.2 GB
Tight Get file →
IQ3_XXS2.8 GB 7.3 GB
Tight Get file →
IQ3_XS3.0 GB 7.5 GB
Tight Get file →
IQ3_S3.1 GB 7.7 GB
Tight Get file →
Q3_K_S3.1 GB 7.7 GB
Tight Get file →
IQ3_M3.3 GB 7.8 GB
Tight Get file →
Q3_K_M3.5 GB 8.0 GB
Tight Get file →
Q3_K_L3.7 GB 8.3 GB
Too big Get file →
IQ4_XS3.8 GB 8.3 GB
Too big Get file →
IQ4_NL4.0 GB 8.5 GB
Too big Get file →
Q4_04.0 GB 8.5 GB
Too big Get file →
Q4_K_S4.0 GB 8.6 GB
Too big Get file →
Q4_K_M4.2 GB 8.7 GB
Too big Get file →
Q4_14.4 GB 8.9 GB
Too big Get file →
Q5_K_S4.8 GB 9.3 GB
Too big Get file →
Q5_K_M4.9 GB 9.5 GB
Too big Get file →
Q6_K5.7 GB 10.2 GB
Too big Get file →

What GPU do you need for DeepSeek Prover V2 7B?

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 the main file (0.0 GB file, about 4.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (3.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.2 GB in use).

Which DeepSeek Prover V2 7B quant should you choose?

Q4_K_M is the usual starting point for DeepSeek Prover V2 7B: it balances file size and quality well. Here it is a 4.2 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

Architecturellama
Parameters6.91B
Layers30
Trained context65,536 tokens
KV cache (fp16)480 KB per token

Source

Quantized bymradermacher
FamilyDeepSeek
Downloads (HF)368
Last updated2025-12-24

Frequently asked questions about DeepSeek Prover V2 7B

How much VRAM does DeepSeek Prover V2 7B need?

About 8.7 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Prover V2 7B on an 8 GB GPU?

Yes, with Q3_K_M: the 3.5 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 Prover V2 7B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.7 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.4 GB and 19 more.

What context length does DeepSeek Prover V2 7B support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 4.0 GB at 8K and 16.1 GB at 32K.

Where can I download DeepSeek Prover V2 7B GGUF?

The files are on Hugging Face in the mradermacher/DeepSeek-Prover-V2-7B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of DeepSeek-Prover-V2-7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More DeepSeek models

All DeepSeek →

Other small models

All small models →