LL

Blackjack-Llama3-21B

LlamaGGUF by mradermacherUpdated 2024-06-25
Download on Hugging Face
Parameters21.3B
Context8K
Layers93
Architecturellama
Smallest quant8.1 GB
Quick answer

Blackjack-Llama3-21B needs about 16.5 GB of memory at Q4_K_M (a 12.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 8.1 GB (Q2_K) to 22.7 GB (Q8_0).

Blackjack‑Llama3‑21B – 21.3B parameter Llama model in GGUF format

Blackjack‑Llama3‑21B is a 21.3B parameter Llama model available as GGUF files. It supports a context length of 8192 tokens and is released under the llama3 license. The model is provided in multiple quantization levels for different memory budgets.

Good at

  • Large context handling
  • High parameter count
  • Versatile quant options

Limits

  • No vision support
  • Requires 8k context for full capability
  • License restricts commercial use

Best for

  • Chatbot development
  • Text generation tasks
  • Fine‑tuning experiments

Who it’s for. Developers and researchers needing a large Llama model with flexible quantization. Suitable for local inference on systems with sufficient VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.1 GB 11.7 GB
Too big Get file →
IQ3_XS9.0 GB 12.6 GB
Too big Get file →
Q3_K_S9.4 GB 13.0 GB
Too big Get file →
IQ3_S9.4 GB 13.1 GB
Too big Get file →
IQ3_M9.7 GB 13.3 GB
Too big Get file →
Q3_K_M10.4 GB 14.0 GB
Too big Get file →
Q3_K_L11.3 GB 14.9 GB
Too big Get file →
IQ4_XS11.7 GB 15.3 GB
Too big Get file →
Q4_K_S12.2 GB 15.9 GB
Too big Get file →
Q4_K_M12.9 GB 16.5 GB
Too big Get file →
Q5_K_S14.7 GB 18.4 GB
Too big Get file →
Q5_K_M15.1 GB 18.8 GB
Too big Get file →
Q6_K17.5 GB 21.1 GB
Too big Get file →
Q8_022.7 GB 26.3 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (8.07 GB, 11.7 GB memory). For 12‑GB VRAM, use IQ3_XS (8.96 GB, 12.6 GB memory). For 16‑GB VRAM, use Q4_K_M (12.89 GB, 16.5 GB memory).

What GPU do you need for Blackjack-Llama3-21B?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q2_K (8.1 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (12.2 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.5 GB file, about 21.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (22.7 GB file, about 26.3 GB in use).

Which Blackjack-Llama3-21B quant should you choose?

Q4_K_M is the usual starting point for Blackjack-Llama3-21B: it balances file size and quality well. Here it is a 12.9 GB file.

The Q8_0 file is 22.7 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 8.1 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
Parameters21.3B
Layers93
Trained context8,192 tokens
KV cache (fp16)372 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3
Downloads (HF)680
Last updated2024-06-25

Frequently asked questions about Blackjack-Llama3-21B

How much VRAM does Blackjack-Llama3-21B need?

About 16.5 GB at Q4_K_M with an 8K context window. That is the 12.9 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 Blackjack-Llama3-21B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Blackjack-Llama3-21B GGUF?

It depends on the quant: Q2_K is 8.1 GB, IQ3_XS is 9.0 GB, Q3_K_S is 9.4 GB, IQ3_S is 9.4 GB, IQ3_M is 9.7 GB, Q3_K_M is 10.4 GB and 8 more.

What context length does Blackjack-Llama3-21B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.

Where can I download Blackjack-Llama3-21B GGUF?

The files are on Hugging Face in the mradermacher/Blackjack-Llama3-21B-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 Blackjack-Llama3-21B use?

Hugging Face lists the license as llama3. 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 Blackjack‑Llama3‑21B on 8 GB VRAM?

Yes, the Q2_K quant file is 8.07 GB and requires approximately 11.7 GB of VRAM at 8k context.

What quant gives the best balance of size and performance?

IQ3_XS offers a good trade‑off with 8.96 GB size and 12.6 GB memory usage.

Is the model suitable for vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →