DE

deepseek math 7b rl

DeepSeekGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters6.91B
Context4K
Layers30
Architecturellama
Smallest quant2.7 GB
Quick answer

deepseek math 7b rl needs about 8.8 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 14 quants, from 2.7 GB (Q2_K) to 7.3 GB (Q8_0).

DeepSeek Math 7B RL – a 6.91B‑parameter math‑focused LLM

DeepSeek Math 7B RL is a 6.91B‑parameter llama‑based model trained on 4096‑token context. It is optimized for mathematical reasoning and chain‑of‑thought prompting. The model is available in multiple GGUF quantizations.

Good at

  • Mathematical reasoning
  • Chain‑of‑thought prompting
  • Step‑by‑step solution generation

Limits

  • No vision support
  • License is MIT with model‑specific terms
  • Requires 8k context for full functionality

Best for

  • Solving algebraic problems
  • Deriving proofs step by step
  • Generating math‑focused explanations

Who it’s for. Developers and researchers needing a lightweight math LLM for inference on local hardware. The model is suitable for integration into educational tools or math tutoring applications.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 5.2 GB
Fits Get file →
IQ3_XS3.0 GB 5.5 GB
Fits Get file →
IQ3_S3.1 GB 5.7 GB
Fits Get file →
Q3_K_S3.1 GB 5.7 GB
Fits Get file →
IQ3_M3.3 GB 5.8 GB
Fits Get file →
Q3_K_M3.5 GB 6.0 GB
Fits Get file →
Q3_K_L3.7 GB 6.3 GB
Fits Get file →
IQ4_XS3.8 GB 6.3 GB
Fits Get file →
Q4_K_S4.0 GB 6.5 GB
Fits Get file →
Q4_K_M4.2 GB 6.7 GB
Fits Get file →
Q5_K_S4.8 GB 7.3 GB
Tight Get file →
Q5_K_M4.9 GB 7.4 GB
Tight Get file →
Q6_K5.7 GB 8.2 GB
Too big Get file →
Q8_07.3 GB 9.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.22 GB file, ~8.8 GB memory). For 12 GB VRAM, Q5_K_M (4.93 GB file, ~9.5 GB memory) or Q6_K (5.67 GB file, ~10.2 GB memory). For 16 GB VRAM, Q8_0 (7.35 GB file, ~11.9 GB memory) offers the highest quality.

What GPU do you need for deepseek math 7b rl?

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: no quant fits at an 8K context.
  • 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 Q8_0 (7.3 GB file, about 11.9 GB in use).

Which deepseek math 7b rl quant should you choose?

Q4_K_M is the usual starting point for deepseek math 7b rl: it balances file size and quality well. Here it is a 4.2 GB file.

The Q8_0 file is 7.3 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.

If memory is tight, the smallest file is Q2_K at 2.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.91B
Layers30
Trained context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized bymradermacher
FamilyDeepSeek
Licenseother
Downloads (HF)692
Last updated2024-05-06

Frequently asked questions about deepseek math 7b rl

How much VRAM does deepseek math 7b rl need?

About 8.8 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 math 7b rl 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 math 7b rl GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, IQ3_S is 3.1 GB, Q3_K_S is 3.1 GB, IQ3_M is 3.3 GB, Q3_K_M is 3.5 GB and 8 more.

What context length does deepseek math 7b rl support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.

Where can I download deepseek math 7b rl GGUF?

The files are on Hugging Face in the mradermacher/deepseek-math-7b-rl-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 math 7b rl 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.

Can I run DeepSeek Math 7B RL on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 8.8 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under MIT with model‑specific terms allowing commercial use.

Other GGUFs of deepseek-math-7b-rl

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More DeepSeek models

All DeepSeek →

Other small models

All small models →