DI

discoresearch_discolm_german_7b_v1

DiscolmGGUF by TheBlokeUpdated 2024-01-24
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

discoresearch_discolm_german_7b_v1 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.7 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

DiscoLM German 7B v1 – a German‑focused LLM in GGUF format

DiscoLM German 7B v1 is a 7 billion‑parameter model based on the Mistral architecture, optimized for German text generation and translation. It supports ChatML prompts and offers structured output via function calling. The model is released under the Apache‑2.0 license.

Good at

  • German language generation
  • Translation between German and English
  • ChatML compatible prompts

Limits

  • No vision support
  • Requires 8 k context for estimates
  • Large VRAM needed for higher quants

Best for

  • German customer support bots
  • Translation services
  • German content creation

Who it’s for. Developers building German‑centric applications who need a local LLM that matches or exceeds GPT‑4 quality in German. The model is suitable for teams that prefer open‑source licensing and local deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (≈5.9 GB memory at 8 k context). With 12 GB VRAM Q5_K_M (≈6.7 GB) is feasible. For 16 GB VRAM Q6_K (≈7.5 GB) provides higher quality. File sizes range from 2.72 GB (Q2_K) to 7.7 GB (Q8_0).

What GPU do you need for discoresearch_discolm_german_7b_v1?

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 Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which discoresearch_discolm_german_7b_v1 quant should you choose?

Q4_K_M is the usual starting point for discoresearch_discolm_german_7b_v1: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 GB, about 1.8 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTheBloke
FamilyDiscolm
Licenseapache-2.0
Downloads (HF)4,827
Last updated2024-01-24

Frequently asked questions about discoresearch_discolm_german_7b_v1

How much VRAM does discoresearch_discolm_german_7b_v1 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 discoresearch_discolm_german_7b_v1 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of discoresearch_discolm_german_7b_v1 GGUF?

It depends on the quant: Q2_K is 2.7 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.1 GB, Q4_K_S is 4.1 GB and 6 more.

What context length does discoresearch_discolm_german_7b_v1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 discoresearch_discolm_german_7b_v1 GGUF?

The files are on Hugging Face in the TheBloke/DiscoLM_German_7b_v1-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 discoresearch_discolm_german_7b_v1 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 DiscoLM German 7B v1 on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 5.9 GB of VRAM at 8 k context.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of DiscoLM_German_7b_v1

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Discolm models

All Discolm →

Other small models

All small models →