QW

Firefly Qwen1.5 En 7b

QwenGGUF by RichardErkhovUpdated 2024-09-10
Download on Hugging Face
Parameters7.72B
Context32K
Layers32
Architectureqwen2
Smallest quant3.1 GB
Quick answer

Firefly Qwen1.5 En 7b needs about 9.6 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 3.1 GB (Q2_K) to 8.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

Firefly Qwen1.5 En 7b – 7.72B parameter English instruction model

Firefly Qwen1.5 En 7b is a 7.72B parameter model based on Qwen2 architecture. It is fine‑tuned with English instruction data using QLoRA on a single V100 GPU. The model supports a context length of 32768 tokens and is released under the apache‑2.0 license.

Good at

  • English instruction following
  • General-purpose text generation
  • Chat‑style interactions

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No official Chinese evaluation

Best for

  • Building lightweight chat assistants
  • Generating short to medium length content
  • Fine‑tuning on custom instruction data

Who it’s for. Developers and researchers who need a small‑to‑medium sized English instruction model for local deployment. The model is suitable for projects that require a balance between performance and resource usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 7.9 GB
Tight Get file →
IQ3_XS3.4 GB 8.2 GB
Too big Get file →
IQ3_S3.6 GB 8.4 GB
Too big Get file →
Q3_K_S3.6 GB 8.4 GB
Too big Get file →
IQ3_M3.7 GB 8.5 GB
Too big Get file →
Q3_K3.9 GB 8.7 GB
Too big Get file →
Q3_K_M3.9 GB 8.7 GB
Too big Get file →
Q3_K_L4.2 GB 9.0 GB
Too big Get file →
IQ4_XS4.3 GB 9.1 GB
Too big Get file →
Q4_04.5 GB 9.3 GB
Too big Get file →
IQ4_NL4.5 GB 9.3 GB
Too big Get file →
Q4_K_S4.5 GB 9.3 GB
Too big Get file →
Q4_K4.8 GB 9.6 GB
Too big Get file →
Q4_K_M4.8 GB 9.6 GB
Too big Get file →
Q4_15.0 GB 9.8 GB
Too big Get file →
Q5_05.4 GB 10.2 GB
Too big Get file →
Q5_K_S5.4 GB 10.2 GB
Too big Get file →
Q5_K5.5 GB 10.3 GB
Too big Get file →
Q5_K_M5.5 GB 10.3 GB
Too big Get file →
Q5_15.8 GB 10.6 GB
Too big Get file →
Q6_K6.3 GB 11.1 GB
Too big Get file →
Q8_08.2 GB 13.0 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 3.1 GB, estimated 7.9 GB memory at 8k context). For 12 GB VRAM, Q4_K (4.77 GB, 9.6 GB memory). For 16 GB VRAM, Q5_K (5.53 GB, 10.3 GB memory).

What GPU do you need for Firefly Qwen1.5 En 7b?

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: the best quant that fits is Q2_K (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.2 GB file, about 13.0 GB in use).

Which Firefly Qwen1.5 En 7b quant should you choose?

Q4_K_M is the usual starting point for Firefly Qwen1.5 En 7b: it balances file size and quality well. Here it is a 4.8 GB file.

The Q8_0 file is 8.2 GB, about 1.7 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 3.1 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

Architectureqwen2
Parameters7.72B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized byRichardErkhov
FamilyQwen
Licenseapache-2.0
Downloads (HF)706
Last updated2024-09-10

Frequently asked questions about Firefly Qwen1.5 En 7b

How much VRAM does Firefly Qwen1.5 En 7b need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 4.8 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 Firefly Qwen1.5 En 7b on an 8 GB GPU?

Yes, with Q2_K: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Firefly Qwen1.5 En 7b GGUF?

It depends on the quant: Q2_K is 3.1 GB, IQ3_XS is 3.4 GB, IQ3_S is 3.6 GB, Q3_K_S is 3.6 GB, IQ3_M is 3.7 GB, Q3_K is 3.9 GB and 16 more.

What context length does Firefly Qwen1.5 En 7b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download Firefly Qwen1.5 En 7b GGUF?

The files are on Hugging Face in the RichardErkhov/YeungNLP_-_firefly-qwen1.5-en-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 Firefly Qwen1.5 En 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 Firefly Qwen1.5 En 7b on 8 GB VRAM?

Yes, the Q2_K quantization requires about 7.9 GB memory at 8k context, which fits within 8 GB VRAM.

Does the model support Chinese language?

The model was trained on English data; Chinese performance has not been evaluated.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Qwen models

All Qwen →

Other small models

All small models →