EC

EchoSwift 700M

EchoswiftGGUF by mradermacherUpdated 2026-10-29
Download on Hugging Face
Parameters742M
Context125K
Layers16
Architecturelfm2
Smallest quant0.0 GB
Quick answer

EchoSwift 700M needs about 1.8 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 0.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

EchoSwift 700M – a lightweight, tool‑aware LLM for mobile assistants

EchoSwift 700M is a 0.742 billion‑parameter language model fine‑tuned for on‑device mobile AI. It supports tool usage and generates single‑file offline web artifacts. The model is optimized for sub‑second agentic responses on edge devices.

Good at

  • Tool‑aware interactions
  • Single‑file offline web artifact generation
  • Structured on‑device agentic tasks

Limits

  • No vision support
  • License type is other
  • No large‑context support beyond 128000 tokens

Best for

  • Mobile AI assistants
  • Edge‑optimized web app generation
  • Tool‑driven task automation

Who it’s for. Developers building private, on‑device mobile assistants who need structured, tool‑aware responses without external dependencies. The model is suitable for edge deployments where latency and offline capability are critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.3 GB
Fits Get file →
IQ1_S0.2 GB 1.5 GB
Fits Get file →
IQ1_M0.2 GB 1.5 GB
Fits Get file →
IQ2_XXS0.2 GB 1.5 GB
Fits Get file →
IQ2_XS0.3 GB 1.6 GB
Fits Get file →
IQ2_S0.3 GB 1.6 GB
Fits Get file →
IQ2_M0.3 GB 1.6 GB
Fits Get file →
Q2_K_S0.3 GB 1.6 GB
Fits Get file →
Q2_K0.3 GB 1.6 GB
Fits Get file →
IQ3_XXS0.3 GB 1.6 GB
Fits Get file →
IQ3_XS0.3 GB 1.7 GB
Fits Get file →
IQ3_S0.4 GB 1.7 GB
Fits Get file →
Q3_K_S0.4 GB 1.7 GB
Fits Get file →
IQ3_M0.4 GB 1.7 GB
Fits Get file →
Q3_K_M0.4 GB 1.7 GB
Fits Get file →
Q3_K_L0.4 GB 1.7 GB
Fits Get file →
IQ4_XS0.4 GB 1.7 GB
Fits Get file →
IQ4_NL0.4 GB 1.8 GB
Fits Get file →
Q4_00.4 GB 1.8 GB
Fits Get file →
Q4_K_S0.4 GB 1.8 GB
Fits Get file →
Q4_K_M0.5 GB 1.8 GB
Fits Get file →
Q4_10.5 GB 1.8 GB
Fits Get file →
Q5_K_S0.5 GB 1.8 GB
Fits Get file →
Q5_K_M0.5 GB 1.8 GB
Fits Get file →
Q6_K0.6 GB 1.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.47 GB file, 1.8 GB memory at 8k context) or Q5_K_M (0.54 GB file, 1.8 GB memory). For tighter budgets, IQ1_S (0.2 GB file, 1.5 GB memory) or IQ1_M (0.22 GB file, 1.5 GB memory) are suitable. Memory estimates are approximate.

What GPU do you need for EchoSwift 700M?

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 Q6_K (0.6 GB file, about 1.9 GB in use).

Which EchoSwift 700M quant should you choose?

Q4_K_M is the usual starting point for EchoSwift 700M: it balances file size and quality well. Here it is a 0.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters742M
Layers16
Trained context128,000 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyEchoswift
Licenseother
Downloads (HF)1,154
Last updated2026-10-29

Frequently asked questions about EchoSwift 700M

How much VRAM does EchoSwift 700M need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.5 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 EchoSwift 700M on an 8 GB GPU?

Yes, with Q6_K: the 0.6 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of EchoSwift 700M GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.2 GB, IQ1_M is 0.2 GB, IQ2_XXS is 0.2 GB, IQ2_XS is 0.3 GB, IQ2_S is 0.3 GB and 19 more.

What context length does EchoSwift 700M support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download EchoSwift 700M GGUF?

The files are on Hugging Face in the mradermacher/EchoSwift-700M-i1-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 EchoSwift 700M 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 EchoSwift 700M on 4 GB VRAM?

The smallest quant is IQ1_S at 0.2 GB file size, but it requires about 1.5 GB memory at 8k context, which is above 4 GB VRAM. You would need a larger VRAM budget.

Does EchoSwift 700M support vision?

No, the model has no vision capabilities.

Other GGUFs of EchoSwift-700M

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Echoswift models

All Echoswift →

Other tiny models

All tiny models →