FO

Fox-1-1.6B-Instruct-v0.1

FoxGGUF by mradermacherUpdated 2024-06-29
Download on Hugging Face
Parameters1.67B
Context8K
Layers32
Architecturellama
Smallest quant0.9 GB
Quick answer

Fox-1-1.6B-Instruct-v0.1 needs about 2.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.9 GB (Q2_K) to 3.3 GB (F16).

Fox-1-1.6B-Instruct-v0.1: 1.6B parameter instruction‑tuned model

Fox-1-1.6B-Instruct-v0.1 is a decoder‑only transformer with 1.67B parameters. It supports an 8K context length and was fine‑tuned on 5B instruction following tokens. The model is released under Apache‑2.0 and is available as GGUF files.

Good at

  • Instruction following
  • Short‑form conversation
  • Code generation

Limits

  • No vision support
  • Requires alignment before production use
  • No multi‑expert architecture

Best for

  • Chatbots with limited GPU memory
  • Rapid prototyping of instruction‑based LLMs
  • Educational demos

Who it’s for. Developers and researchers who need a small, instruction‑tuned language model that can run on modest hardware. The model is suitable for experimentation and low‑resource deployments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.9 GB 1.9 GB
Fits Get file →
IQ3_XS0.9 GB 1.9 GB
Fits Get file →
Q3_K_S0.9 GB 2.0 GB
Fits Get file →
IQ3_S0.9 GB 2.0 GB
Fits Get file →
IQ3_M1.0 GB 2.0 GB
Fits Get file →
Q3_K_M1.0 GB 2.0 GB
Fits Get file →
Q3_K_L1.0 GB 2.1 GB
Fits Get file →
IQ4_XS1.1 GB 2.1 GB
Fits Get file →
Q4_K_S1.1 GB 2.1 GB
Fits Get file →
Q4_K_M1.1 GB 2.2 GB
Fits Get file →
Q5_K_S1.2 GB 2.3 GB
Fits Get file →
Q5_K_M1.2 GB 2.3 GB
Fits Get file →
Q6_K1.4 GB 2.4 GB
Fits Get file →
Q8_01.8 GB 2.8 GB
Fits Get file →
F163.3 GB 4.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.12 GB file, ~2.2 GB memory) or Q5_K_S (1.22 GB file, ~2.3 GB memory). For 4 GB VRAM, Q3_K_S (0.93 GB file, ~2 GB memory) is the largest that fits. Lower quants like Q2_K (0.86 GB file, ~1.9 GB memory) provide the smallest memory footprint.

What GPU do you need for Fox-1-1.6B-Instruct-v0.1?

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: the best quant that fits is Q8_0 (1.8 GB file, about 2.8 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.3 GB file, about 4.4 GB in use).

Which Fox-1-1.6B-Instruct-v0.1 quant should you choose?

Q4_K_M is the usual starting point for Fox-1-1.6B-Instruct-v0.1: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.8 GB, about 1.6 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 0.9 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
Parameters1.67B
Layers32
Trained context8,192 tokens
KV cache (fp16)64 KB per token

Source

Quantized bymradermacher
FamilyFox
Licenseapache-2.0
Downloads (HF)764
Last updated2024-06-29

Frequently asked questions about Fox-1-1.6B-Instruct-v0.1

How much VRAM does Fox-1-1.6B-Instruct-v0.1 need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Fox-1-1.6B-Instruct-v0.1 on an 8 GB GPU?

Yes, with F16: the 3.3 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Fox-1-1.6B-Instruct-v0.1 GGUF?

It depends on the quant: Q2_K is 0.9 GB, IQ3_XS is 0.9 GB, Q3_K_S is 0.9 GB, IQ3_S is 0.9 GB, IQ3_M is 1.0 GB, Q3_K_M is 1.0 GB and 9 more.

What context length does Fox-1-1.6B-Instruct-v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.5 GB at 8K.

Where can I download Fox-1-1.6B-Instruct-v0.1 GGUF?

The files are on Hugging Face in the mradermacher/Fox-1-1.6B-Instruct-v0.1-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 Fox-1-1.6B-Instruct-v0.1 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 Fox-1-1.6B-Instruct-v0.1 on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_S quants will fit within 8 GB VRAM, with estimated memory usage of ~2.2–2.3 GB at 8K context.

Is the model suitable for production chat applications?

The model requires alignment before production use; a chat version will be released soon.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Fox-1-1.6B-Instruct-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Fox models

All Fox →

Other tiny models

All tiny models →