LL

models--fireworks-ai--firefunction-v2

LlamaGGUF by MaziyarPanahiUpdated 2024-06-20
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

models--fireworks-ai--firefunction-v2 needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 16 quants, from 15.3 GB (IQ1_S) to 141.1 GB.

FireFunction V2 – a 71B Llama model optimized for function calling

FireFunction V2 is a 71 billion‑parameter Llama model with an 8 k context window. It is tuned for general instruction following and both single and parallel function calls. The model is released under the llama3 license and supports up to 20 function specs simultaneously.

Good at

  • Function calling with up to 20 specs
  • General instruction following
  • Parallel function calls

Limits

  • 8 k context window only
  • Not optimized for 100+ function specs or nested calls
  • Requires commercial license for deployment

Best for

  • Chatbots needing function integration
  • API wrappers that call external services
  • Structured data extraction tasks

Who it’s for. Developers building local LLM applications that require reliable function calling. The model is suitable for teams that can host the 71 billion‑parameter model and need a function‑aware assistant.

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_XS21.1 GB 24.3 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_M34.3 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 →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q6_K57.9 GB (6 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (6 parts) 78.2 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 VRAM). For 16 GB VRAM, IQ1_M (16.75 GB file, ~19.9 GB VRAM). For 24 GB VRAM, IQ2_XS (21.14 GB file, ~24.3 GB VRAM). Larger VRAM allows higher‑quality quants such as Q3_K_M or Q4_K_M.

What GPU do you need for models--fireworks-ai--firefunction-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: 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 IQ1_M (16.8 GB file, about 19.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which models--fireworks-ai--firefunction-v2 quant should you choose?

Q4_K_M is the usual starting point for models--fireworks-ai--firefunction-v2: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 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 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 byMaziyarPanahi
FamilyLlama
Licensellama3
Downloads (HF)38,818
Last updated2024-06-20

Frequently asked questions about models--fireworks-ai--firefunction-v2

How much VRAM does models--fireworks-ai--firefunction-v2 need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 models--fireworks-ai--firefunction-v2 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 models--fireworks-ai--firefunction-v2 GGUF?

It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XS is 21.1 GB, Q2_K is 26.4 GB, IQ3_XS is 29.3 GB, Q3_K_S is 30.9 GB and 10 more.

What context length does models--fireworks-ai--firefunction-v2 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 models--fireworks-ai--firefunction-v2 GGUF?

The files are on Hugging Face in the MaziyarPanahi/firefunction-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 models--fireworks-ai--firefunction-v2 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 FireFunction V2 on 8 GB VRAM?

Yes, using the IQ1_S quant which requires about 18.5 GB VRAM at 8 k context.

Does the model support vision or image inputs?

No, the model only handles text and function calls.

What license is required to use this model?

The model is released under the llama3 license, which permits commercial use with the appropriate license terms.

Other GGUFs of llama-3-firefunction-v2

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other large models

All large models →