BE

BetterWright K2 Horizon 7B Uno

BetterwrightGGUF by mradermacherUpdated 2026-10-15
Download on Hugging Face
Parameters9B
Context512K
Layers36
Architecturek2-horizon
Smallest quant0.0 GB
Quick answer

BetterWright K2 Horizon 7B Uno needs about 7.3 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

BetterWright K2 Horizon 7B Uno – a fine‑tuned browser‑driving LLM

BetterWright K2 Horizon 7B Uno is a 9‑billion‑parameter model fine‑tuned on 3,840 BetterWright agent trajectories. It supports tool use and runs inside the BetterWright harness. The model is text‑only and uses a K2‑Horizon architecture.

Good at

  • Tool‑based browser interaction
  • No‑reasoning mode for fast responses
  • Fine‑tuned for BetterWright workflows

Limits

  • Text‑only, no vision
  • Requires BetterWright system prompt and tools
  • No reinforcement learning or benchmark claims

Best for

  • Automated web browsing tasks
  • Tool‑centric agent pipelines
  • Fast inference with Uno adapter

Who it’s for. Developers building agents that need to browse the web using the BetterWright framework. The model is ideal for those who want a fine‑tuned, tool‑aware LLM without additional RL training.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ1_S2.5 GB 4.2 GB
Fits Get file →
IQ1_M2.7 GB 4.4 GB
Fits Get file →
IQ2_XXS2.9 GB 4.6 GB
Fits Get file →
IQ2_XS3.1 GB 4.8 GB
Fits Get file →
IQ2_S3.3 GB 5.0 GB
Fits Get file →
IQ2_M3.5 GB 5.2 GB
Fits Get file →
Q2_K_S3.6 GB 5.3 GB
Fits Get file →
Q2_K3.8 GB 5.5 GB
Fits Get file →
IQ3_XXS3.8 GB 5.5 GB
Fits Get file →
IQ3_XS4.1 GB 5.8 GB
Fits Get file →
Q3_K_S4.3 GB 6.0 GB
Fits Get file →
IQ3_S4.3 GB 6.0 GB
Fits Get file →
IQ3_M4.4 GB 6.1 GB
Fits Get file →
Q3_K_M4.6 GB 6.3 GB
Fits Get file →
Q3_K_L4.9 GB 6.7 GB
Fits Get file →
IQ4_XS5.1 GB 6.8 GB
Fits Get file →
Q4_05.4 GB 7.1 GB
Fits Get file →
IQ4_NL5.4 GB 7.1 GB
Fits Get file →
Q4_K_S5.4 GB 7.1 GB
Fits Get file →
Q4_K_M5.6 GB 7.3 GB
Tight Get file →
Q4_15.8 GB 7.5 GB
Tight Get file →
Q5_K_S6.3 GB 8.0 GB
Too big Get file →
Q5_K_M6.5 GB 8.2 GB
Too big Get file →
Q6_K7.4 GB 9.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.53 GB, 4.2 GB memory) or IQ1_M (2.67 GB, 4.4 GB memory). With 12 GB VRAM, Q4_K_M (5.59 GB, 7.3 GB memory) or Q5_K_S (6.34 GB, 8 GB memory) provide a good balance of size and performance. Larger VRAM allows Q6_K (7.39 GB, 9.1 GB memory).

What GPU do you need for BetterWright K2 Horizon 7B Uno?

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 the main file (0.0 GB file, about 1.7 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_S (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (6.3 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.4 GB file, about 9.1 GB in use).

Which BetterWright K2 Horizon 7B Uno quant should you choose?

Q4_K_M is the usual starting point for BetterWright K2 Horizon 7B Uno: it balances file size and quality well. Here it is a 5.6 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

Architecturek2-horizon
Parameters9B
Layers36
Trained context524,288 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)3,478
Last updated2026-10-15

Frequently asked questions about BetterWright K2 Horizon 7B Uno

How much VRAM does BetterWright K2 Horizon 7B Uno need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.6 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 BetterWright K2 Horizon 7B Uno on an 8 GB GPU?

Yes, with Q5_K_S: the 6.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of BetterWright K2 Horizon 7B Uno GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.5 GB, IQ1_M is 2.7 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.3 GB and 19 more.

What context length does BetterWright K2 Horizon 7B Uno support?

The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download BetterWright K2 Horizon 7B Uno GGUF?

The files are on Hugging Face in the mradermacher/BetterWright-K2-Horizon-7B-Uno-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 BetterWright K2 Horizon 7B Uno 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 BetterWright K2 Horizon 7B Uno on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations. They fit within 8 GB VRAM and use about 4.2–4.4 GB memory at 8k context.

Does this model support vision or image generation?

No. The model is text‑only and does not include vision capabilities.

What tools does it support?

It supports the browser, done, and ask tools used in BetterWright agent workflows.

Other GGUFs of BetterWright-K2-Horizon-7B-Uno

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Betterwright models

All Betterwright →

Other small models

All small models →