LL

Higgs-Llama-3-70B

LlamaGGUF by legraphistaUpdated 2024-06-06
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

Higgs-Llama-3-70B needs about 35.1 GB of memory at IQ3_M (a 31.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 25 quants, from 15.3 GB (IQ1_S) to 141.1 GB.

Higgs‑Llama‑3‑70B: 70.6B‑parameter Llama model fine‑tuned for role‑playing and instruction following

Higgs‑Llama‑3‑70B is a 70.6B‑parameter Llama model post‑trained from Meta‑Llama‑3‑70B. It is tuned for role‑playing while remaining competitive on general‑domain instruction‑following and reasoning tasks. The model was trained with supervised fine‑tuning, preference pairs, and iterative preference optimization.

Good at

  • Role‑playing with system messages
  • General instruction following
  • Reasoning on benchmarks

Limits

  • No vision support
  • Requires large VRAM for higher quantizations
  • License is other, not open source

Best for

  • Chatbots needing role consistency
  • Instruction‑driven applications
  • Reasoning tasks in research

Who it’s for. Developers building chat interfaces that require consistent role behavior. Researchers needing a large Llama model with specialized alignment for role‑playing scenarios.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.3 GB 18.5 GB
Too big Get file →
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_S22.2 GB 25.4 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K_S24.5 GB 27.7 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
IQ4_NL40.1 GB 43.2 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB (2 parts) 51.8 GB
Too big Get file →
Q5_K49.9 GB (2 parts) 53.1 GB
Too big Get file →
Q6_K57.9 GB (3 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (3 parts) 78.2 GB
Too big Get file →
BF16141.1 GB (6 parts) 144.3 GB
Too big Get file →
—141.1 GB (6 parts) 144.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (15.34 GB file, 18.5 GB memory at 8k context). For 16 GB VRAM, IQ2_S (22.24 GB file, 25.4 GB memory). For 24 GB VRAM, Q4_K (42.52 GB file, 45.7 GB memory). Split files can be merged with gguf‑split.

What GPU do you need for Higgs-Llama-3-70B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K (42.5 GB file, about 45.7 GB in use).

Which Higgs-Llama-3-70B quant should you choose?

IQ3_M (31.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 15.3 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
Parameters70.6B
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bylegraphista
FamilyLlama
Licenseother
Downloads (HF)1,690
Last updated2024-06-06

Frequently asked questions about Higgs-Llama-3-70B

How much VRAM does Higgs-Llama-3-70B need?

About 35.1 GB at IQ3_M with an 8K context window. That is the 31.9 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 Higgs-Llama-3-70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Higgs-Llama-3-70B GGUF?

It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, IQ2_M is 24.1 GB and 19 more.

What context length does Higgs-Llama-3-70B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Higgs-Llama-3-70B GGUF?

The files are on Hugging Face in the legraphista/Higgs-Llama-3-70B-IMat-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 Higgs-Llama-3-70B 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 Higgs‑Llama‑3‑70B on 8 GB VRAM?

Use the IQ1_S quantization; it requires 18.5 GB of VRAM at 8k context, which is above 8 GB, so it will not fit. A lower‑parameter model would be needed.

Does the model support vision?

No, the model has no vision capabilities.

How many shards are needed for the Q5_K quant?

The Q5_K quant is split into 2 shards.

Other GGUFs of Higgs-Llama-3-70B

Similar models

Browse all →

More from legraphista

All by legraphista →

More Llama models

All Llama →

Other large models

All large models →