VE

delcos_velara-11b-v2

VelaraGGUF by TheBlokeUpdated 2024-01-10
Download on Hugging Face
Parameters11.4B
Context32K
Layers51
Architecturellama
Smallest quant4.8 GB
Quick answer

delcos_velara-11b-v2 needs about 9.1 GB of memory at Q4_K_M (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 4.8 GB (Q2_K) to 12.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.8 GB.

Velara‑11B‑v2 – a 11.4B llama model focused on chat fidelity

Velara‑11B‑v2 is a 11.4B parameter llama model designed for conversational use. It emphasizes staying in context, sticking to character, and avoiding generic responses. The model is available in multiple GGUF quantisations.

Good at

  • Context‑aware chat
  • Character consistency
  • Avoiding generic answers

Limits

  • No vision support
  • License cc‑by‑nc‑nd‑4.0
  • Requires GPU for best performance

Best for

  • Chat assistants
  • Role‑playing characters
  • Interactive storytelling

Who it’s for. Developers and hobbyists who need a local chat model that stays in context and follows prompts closely. The model is suitable for building character‑driven applications and for users who prefer uncensored, conversational AI.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 7.0 GB
Fits Get file →
Q3_K_S4.9 GB 7.2 GB
Fits Get file →
Q3_K_M5.5 GB 7.7 GB
Tight Get file →
Q3_K_L6.0 GB 8.2 GB
Too big Get file →
Q4_06.4 GB 8.7 GB
Too big Get file →
Q4_K_S6.5 GB 8.7 GB
Too big Get file →
Q4_K_M6.8 GB 9.1 GB
Too big Get file →
Q5_07.8 GB 10.1 GB
Too big Get file →
Q5_K_S7.8 GB 10.1 GB
Too big Get file →
Q5_K_M8.1 GB 10.3 GB
Too big Get file →
Q6_K9.3 GB 11.6 GB
Too big Get file →
Q8_012.1 GB 14.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (6.85 GB file, ~9.1 GB memory). For 12 GB VRAM, Q5_K_M (8.06 GB file, ~10.3 GB memory) is a good balance. If more VRAM is available, Q6_K (9.34 GB file, ~11.6 GB memory) offers higher quality.

What GPU do you need for delcos_velara-11b-v2?

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 (5.5 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (9.3 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.1 GB file, about 14.3 GB in use).

Which delcos_velara-11b-v2 quant should you choose?

Q4_K_M is the usual starting point for delcos_velara-11b-v2: it balances file size and quality well. Here it is a 6.8 GB file.

The Q8_0 file is 12.1 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 4.8 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
Parameters11.4B
Layers51
Trained context32,768 tokens
KV cache (fp16)204 KB per token

Source

Quantized byTheBloke
FamilyVelara
Downloads (HF)1,499
Last updated2024-01-10

Frequently asked questions about delcos_velara-11b-v2

How much VRAM does delcos_velara-11b-v2 need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 6.8 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 delcos_velara-11b-v2 on an 8 GB GPU?

Yes, with Q3_K_M: the 5.5 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of delcos_velara-11b-v2 GGUF?

It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 4.9 GB, Q3_K_M is 5.5 GB, Q3_K_L is 6.0 GB, Q4_0 is 6.4 GB, Q4_K_S is 6.5 GB and 6 more.

What context length does delcos_velara-11b-v2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.8 GB at 32K.

Where can I download delcos_velara-11b-v2 GGUF?

The files are on Hugging Face in the TheBloke/Velara-11B-V2-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 delcos_velara-11b-v2 use?

Hugging Face lists the license as cc-by-nc-nd-4.0. 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 Velara‑11B‑v2 on 8 GB VRAM?

Yes, using the Q4_K_M quantisation requires about 9.1 GB of VRAM at 8 k context.

Does Velara‑11B‑v2 support image inputs?

No, the model has no vision capability.

What license applies to Velara‑11B‑v2?

The model is licensed under cc‑by‑nc‑nd‑4.0, allowing non‑commercial use with attribution.

Other GGUFs of Velara-11B-V2

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Velara models

All Velara →

Other medium models

All medium models →