FI

Finch 7b

FinchGGUF by latestissueUpdated 2024-10-25
Download on Hugging Face
Parameters7.64B
Context1024K
Layers32
Architecturerwkv6
Smallest quant3.0 GB
Quick answer

Finch 7b needs about 5.7 GB of memory at Q4_K (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 23 quants, from 3.0 GB (Q2_K) to 30.5 GB (F32).

Finch 7b – a 7 billion‑parameter RWKV‑6 model in GGUF format

Finch 7b is a 7 billion‑parameter RWKV‑6 architecture model released under the Apache‑2.0 license. It supports a maximum context length of 1,048,576 tokens and is available in multiple quantized GGUF files.

Good at

  • Large context handling
  • Efficient inference with low‑bit quantization
  • Apache‑2.0 licensed for reuse

Limits

  • No vision capabilities
  • Requires large VRAM for higher‑bit quantizations
  • No mixture of experts

Best for

  • Long‑form text generation
  • Context‑heavy dialogue systems
  • Fine‑tuning on custom corpora

Who it’s for. Developers and researchers needing a large‑context language model that can be run locally with GGUF and llama.cpp. The model is suitable for projects that require flexible quantization to match available GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 3.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.2 GB
Fits Get file →
IQ3_S3.7 GB 4.6 GB
Fits Get file →
Q3_K3.7 GB 4.6 GB
Fits Get file →
Q3_K_L3.7 GB 4.6 GB
Fits Get file →
IQ4_XS4.4 GB 5.5 GB
Fits Get file →
IQ4_NL4.7 GB 5.7 GB
Fits Get file →
Q4_04.7 GB 5.7 GB
Fits Get file →
Q4_04.7 GB 5.7 GB
Fits Get file →
Q4_04.7 GB 5.7 GB
Fits Get file →
Q4_04.7 GB 5.7 GB
Fits Get file →
Q4_K4.7 GB 5.7 GB
Fits Get file →
Q4_K_S4.7 GB 5.7 GB
Fits Get file →
Q4_15.1 GB 6.2 GB
Fits Get file →
Q5_05.6 GB 6.7 GB
Fits Get file →
Q5_K5.6 GB 6.7 GB
Fits Get file →
Q5_K_S5.6 GB 6.7 GB
Fits Get file →
Q5_16.0 GB 7.2 GB
Tight Get file →
Q6_K6.5 GB 7.8 GB
Tight Get file →
Q8_08.4 GB 9.9 GB
Too big Get file →
BF1615.4 GB 17.8 GB
Too big Get file →
F1615.5 GB 17.9 GB
Too big Get file →
F3230.5 GB 34.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (≈5.7 GB memory at 8 k context). For 12 GB VRAM, Q5_0 (≈6.7 GB) or Q6_K (≈7.8 GB) are suitable. Higher‑bit options like Q8_0 or BF16 require 10 GB+ VRAM and are not recommended for limited memory setups.

What GPU do you need for Finch 7b?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q2_K (3.0 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.5 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.4 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.4 GB file, about 9.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.5 GB file, about 17.9 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (15.5 GB file, about 17.9 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (30.5 GB file, about 34.7 GB in use).

Which Finch 7b quant should you choose?

Q4_K (4.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 3.0 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

Architecturerwkv6
Parameters7.64B
Layers32
Trained context1,048,576 tokens

Source

Quantized bylatestissue
FamilyFinch
Licenseapache-2.0
Downloads (HF)6,488
Last updated2024-10-25

Frequently asked questions about Finch 7b

How much VRAM does Finch 7b need?

About 5.7 GB at Q4_K with an 8K context window. That is the 4.7 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 Finch 7b on an 8 GB GPU?

Yes, with Q6_K: the 6.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Finch 7b GGUF?

It depends on the quant: Q2_K is 3.0 GB, IQ3_XXS is 3.3 GB, IQ3_S is 3.7 GB, Q3_K is 3.7 GB, Q3_K_L is 3.7 GB, IQ4_XS is 4.4 GB and 17 more.

What context length does Finch 7b support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download Finch 7b GGUF?

The files are on Hugging Face in the latestissue/rwkv-6-finch-7b-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 Finch 7b 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 Finch 7b on 8 GB VRAM?

Yes, using the Q4_0 quantization which uses about 5.7 GB of VRAM at 8 k context.

Does Finch 7b support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from latestissue

All by latestissue →

More Finch models

All Finch →

Other small models

All small models →