selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

NousResearch logo

Arete-27B

NousResearch·Instruct·released 6 Nov 2026

Apache 2.027.4B256K ctx ≈19 GB
Your GPU
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q4_K_M
All 5 runners ↓

We post-trained over Alibaba's Qwen3.8-27B to reinforce western values on a Chinese-trained model. We call this new model Arete-27B.

Notify me when

How much VRAM does Arete-27B need?

At Q4_K_M Arete-27B needs about 19 GB with an 8K context (19 GB at Q4, 56 GB at full precision). Pick your GPU to see what fits and how fast it runs.

--vram
any
--gpus
--quant

Needs: ≈19 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.

Change quant, context or KV cache to compare
Advanced: context 8K · KV cache 16-bit
Context
KV cache

Smallest GPU for each quant and context (KV cache 16-bit)

Quantisation8K16K32K64K128K256K
Q3_K_M
Q4_K_M
Q5_K_M
Q6_K
Q8_0
FP16

≤16 GB card24–32 GB48–96 GBmore

QuantisationQualityWeightsKV cacheTotal
Q2_KHeavy lossSmallest, noticeably worse qualityHeavy loss9.9 GB file2.0 GB≈13 GB
Q3_K_MNoticeable lossSmall, some quality lossNoticeable loss12 GB file2.0 GB≈15 GB
Q4_K_MrecommendedSmall lossRecommended default for local useSmall loss16 GB file2.0 GB≈19 GB
Q5_K_MNear-losslessNear-lossless for most tasksNear-lossless19 GB file2.0 GB≈23 GB
Q6_KNear-losslessPractically losslessNear-lossless22 GB file2.0 GB≈26 GB
Q8_0LosslessLossless in practice, twice the size of Q4Lossless27 GB file2.0 GB≈31 GB
FP16 / BF16LosslessFull precision, as releasedLossless50 GB file2.0 GB≈55 GB

Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.

How to pick a quant

Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.

  • LosslessF16, Q8_0
  • Near-losslessQ6_K, Q5_K_M
  • Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
  • Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
  • Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K

Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B

How much context fits?

Model quant
KV cache

At 8K context, Q4_K_M needs ≈19 GB(16 GB weights + 2.0 GB KV cache + 1.3 GB overhead). Pick a GPU above to see how much context fits.

0204060801001K2K4K8K16K32K64K128K256KGB

Weights + overheadKV cache

Can the Tesla P40 run Arete-27B? →

Speed vs quality per quant

Smaller quants run faster and fit in less memory, but lose quality.

Q2_KQ3_K_MQ4_K_MQ5_K_MQ6_KQ8_0F16

Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.

Real-world speed of Arete-27B

Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →

No medians yet. Be one of the first 3 to report a setup.

All reports

Run Arete-27B locally

--quantQ4_K_Mdefault; pick your GPU to tailor itbartowski/NousResearch_Arete-27B-GGUF

Q4_K_M straight from Hugging Facedocs
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q4_K_M

Install Ollama

OpenAI-compatible server with a web UIdocs
llama-server -hf bartowski/NousResearch_Arete-27B-GGUF:Q4_K_M

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

Install llama.cpp

Download with the lms CLIdocs
lms get bartowski/NousResearch_Arete-27B-GGUF@Q4_K_M

Then load it from the LM Studio app or with `lms load`.

Install LM Studio

Serve an OpenAI-compatible APIdocs
vllm serve NousResearch/Arete-27B
Smaller FP8 builddocs
vllm serve processreap/Arete-27B-FP8
Docker Compose (NVIDIA)docs
yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: NousResearch/Arete-27B
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 8000.

Install vLLM

Serve an OpenAI-compatible APIdocs
sglang serve NousResearch/Arete-27B --host 0.0.0.0 --port 30000
Docker Compose (NVIDIA)docs
yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve NousResearch/Arete-27B --host 0.0.0.0 --port 30000
    ports:
      - "30000:30000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 30000.

Install SGLang

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
SargeDev/Arete-27B-Uncensored-NVFP4-FP8SafetensorsNVFP4—2.5K
veladan/Arete-27B-NVFP4SafetensorsNVFP4—337
processreap/Arete-27B-FP8SafetensorsFP8—136
bartowski/NousResearch_Arete-27B-GGUFGGUFIQ2_XXS8.6 GB68.2K
bartowski/NousResearch_Arete-27B-GGUFGGUFIQ2_XS8.8 GB68.2K
bartowski/NousResearch_Arete-27B-GGUFGGUFIQ2_S9.4 GB68.2K
bartowski/NousResearch_Arete-27B-GGUFGGUFIQ2_M10 GB68.2K
bartowski/NousResearch_Arete-27B-GGUFGGUFQ2_K11 GB68.2K
bartowski/NousResearch_Arete-27B-GGUFGGUFIQ3_XXS12 GB68.2K
bartowski/NousResearch_Arete-27B-GGUFGGUFQ3_K_S13 GB68.2K

About Arete-27B

We post-trained over Alibaba's Qwen3.8-27B to reinforce western values on a Chinese-trained model. We call this new model Arete-27B. Open source models give labs the raw tools to mold intelligence to varied preferences. The values a model ships with should not be the only values its users get to choose from. We observed firsthand refusals, deflections, and CCP-framed answers on politically sensitive topics in Qwen3.8-27B, and post-trained to alter those biases. On our evaluation, Arete-27B raised its fact score from 2.32 to 2.98 out of 5 and cut answers containing propaganda from 22% to 0.9%. The improvement held in all seven value categories, without a meaningful regression on the general-capability and agentic benchmarks we ran. That is not to claim that we remedied all behaviors associated with the extant viewpoint, but that we have addressed a potential root cause. We believe it's important that labs and researchers continue to create models that align with their values and worldviews, and we are thankful that companies like Alibaba provide the raw materials to do so. Blog post · Evaluation We used supervised fine-tuning only. No RL, no preference optimization, and no architectural modification. We focused on seven value categories: • Freedom of expression • State ideology • State versus free market • Education • Data privacy and surveillance • Democracy • Environmental Policy

Full model card on Hugging Face →

Alternatives to Arete-27B

All alternatives →

NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents.

31.6BA3B256K ctx openmdw-1.1
996KAug 2026gguf
farbodtavakkoli logo

OTel-2.0-LLM-31B-IT

farbodtavakkoli·Chat

≈27 GB

Versioning notice: This card describes the current OTel 2.0 OSFT checkpoint. The model weights may be updated over time. For reproducible evaluation or production deployment, pin a specific model revision, checkpoint hash, or release tag rather than relying on the floating latest version.

31.3B256K ctx Apache 2.0
835.5KJul 2026gguf
ornith-ai logo

Ornith-1.0-35B

ornith-ai·Chat

≈22 GB

Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.

35BA3.8B256K ctx MIT
1.5MJun 2026gguf
poolside logo

Laguna-XS-2.1

poolside·Chat

≈22 GB

Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.

33.4BA2.2B256K ctx Custom licence
615.8KJun 2026ollama
zai-org logo

GLM-4.7-Flash

zai-org·Chat

≈26 GB

👋 Join our Discord community. 📖 Check out the GLM-4.7 technical blog , technical report(GLM-4.5) . 📍 Use GLM-4.7-Flash API services on Z.ai API Platform. 👉 One click to GLM-4.7 .

31.2BA4.6B198K ctx MIT
1.1MJan 2026ollama

Nemotron-3-Nano-30B-A3B-BF16 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response.

31.6BA3B256K ctx nvidia-nemotron-open-model-license
1.4MDec 2025gguf

Arete-27B FAQ

How much VRAM does Arete-27B need?
About 19 GB at Q4_K_M with an 8K context. Q8_0 needs about 31 GB and full precision about 56 GB. Longer contexts need more memory for the KV cache.
Can Arete-27B run on the Tesla P40?
Yes. It fits at Q5_K_M (about 23 GB), at an estimated 9.8 tokens/s. It fits comfortably on the Radeon RX 7900 XTX, Instinct MI50 32GB, RTX 5090.
Can I use Arete-27B commercially?
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.
What is the context length of Arete-27B?
262,144 tokens (256K). The full window needs far more memory than an 8K context.
How do I run Arete-27B with Ollama or llama.cpp?
With Ollama: ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q4_K_M. With llama.cpp: llama-server -hf bartowski/NousResearch_Arete-27B-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.