NE

NeoHorse-1-4B

NeohorseGGUF by TokenRhythmUpdated 2026-09-10
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.7 GB
Quick answer

NeoHorse-1-4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.7 GB (Q4_K_M) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

NeoHorse‑1‑4B: a 4B causal language model focused on recursive self‑improvement

NeoHorse‑1‑4B is a 4B parameter causal language model derived from Qwen3.5‑4B. It is post‑trained for text‑based agent harnesses, tool use, coding, and instruction following. The model is available in GGUF format for local inference.

Good at

  • Tool‑aware reasoning
  • Agentic post‑training
  • Instruction following

Limits

  • No vision weights included
  • Large context size requires significant VRAM
  • License is Apache‑2.0

Best for

  • Local text‑only inference
  • Agent harness prototyping
  • Tool‑use scripting

Who it’s for. Developers building text‑only agents or experimenting with recursive self‑improvement. The model is suitable for users who need a lightweight, open‑source language model for local deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q5_K_M3.1 GB 4.6 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
BF168.4 GB 10.0 GB
Too big Get file →
F168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.71 GB, ~4.3 GB RAM). For 12 GB VRAM, Q5_K_M (3.07 GB, ~4.6 GB RAM). If more memory is available, Q8_0 or BF16 provide higher precision.

What GPU do you need for NeoHorse-1-4B?

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: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).

Which NeoHorse-1-4B quant should you choose?

Q4_K_M is the usual starting point for NeoHorse-1-4B: it balances file size and quality well. Here it is a 2.7 GB file.

The Q8_0 file is 4.5 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTokenRhythm
FamilyNeohorse
Licenseapache-2.0
Downloads (HF)9,739
Last updated2026-09-10

Frequently asked questions about NeoHorse-1-4B

How much VRAM does NeoHorse-1-4B need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 NeoHorse-1-4B on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NeoHorse-1-4B GGUF?

It depends on the quant: Q4_K_M is 2.7 GB, Q5_K_M is 3.1 GB, Q8_0 is 4.5 GB, BF16 is 8.4 GB, F16 is 8.4 GB.

What context length does NeoHorse-1-4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download NeoHorse-1-4B GGUF?

The files are on Hugging Face in the TokenRhythm/NeoHorse-1-4B-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 NeoHorse-1-4B 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 NeoHorse‑1‑4B on 8 GB VRAM?

Yes, the Q4_K_M quantized model requires about 4.3 GB VRAM at 8 k context, which fits in 8 GB.

Does NeoHorse‑1‑4B support vision tasks?

No, the released weights are text‑only; vision weights are not included.

What license applies to NeoHorse‑1‑4B?

The model is released under the Apache‑2.0 license.

Other GGUFs of NeoHorse-1-4B

Similar models

Browse all →

More from TokenRhythm

All by TokenRhythm →

More Neohorse models

All Neohorse →

Other small models

All small models →