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.

ibm-granite logo

granite-4.1-8b-llmon-preview

ibm-granite·Instruct·released 1 Oct 2026

Apache 2.08.8B128K ctx ≈7.0 GB
Your GPU
vllm serve ibm-granite/granite-4.1-8b-llmon-preview
All 3 runners ↓

Model Summary: Granite-4.1-8B-LLMON-preview is an 8B-parameter instruct model fine-tuned from Granite-4.1-8B-base to consume prompts in LLMON (LLM Object Notation) instead of a conventional chat template.

Notify me when

How much VRAM does granite-4.1-8b-llmon-preview need?

At Q4_K_M granite-4.1-8b-llmon-preview needs about 7.0 GB with an 8K context (7.0 GB at Q4, 19 GB at full precision). Pick your GPU to see what fits and how fast it runs.

--vram
any
--gpus
--quant

Needs: ≈7.0 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)

Quantisation4K8K16K32K64K128K
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 loss2.7 GB 1.3 GB≈4.6 GB
Q3_K_MNoticeable lossSmall, some quality lossNoticeable loss4.0 GB 1.3 GB≈6.0 GB
Q4_K_MrecommendedSmall lossRecommended default for local useSmall loss5.0 GB 1.3 GB≈7.0 GB
Q5_K_MNear-losslessNear-lossless for most tasksNear-lossless5.8 GB 1.3 GB≈7.9 GB
Q6_KNear-losslessPractically losslessNear-lossless6.7 GB 1.3 GB≈8.8 GB
Q8_0LosslessLossless in practice, twice the size of Q4Lossless8.7 GB 1.3 GB≈11 GB
FP16 / BF16LosslessFull precision, as releasedLossless16 GB 1.3 GB≈19 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.

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 ≈7.0 GB(5.0 GB weights + 1.3 GB KV cache + 0.8 GB overhead). Pick a GPU above to see how much context fits.

01020301K2K4K8K16K32K64K128KGB

Weights + overheadKV cache

Can the RTX 4060 run granite-4.1-8b-llmon-preview? →

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 granite-4.1-8b-llmon-preview

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 granite-4.1-8b-llmon-preview locally

These commands load the original weights from Hugging Face.

Serve an OpenAI-compatible APIdocs
vllm serve ibm-granite/granite-4.1-8b-llmon-preview
Smaller FP8 builddocs
vllm serve liodon-ai/granite-4.1-8b-llmon-preview-FP8
Docker Compose (NVIDIA)docs
yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: ibm-granite/granite-4.1-8b-llmon-preview
    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 ibm-granite/granite-4.1-8b-llmon-preview --host 0.0.0.0 --port 30000
Docker Compose (NVIDIA)docs
yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve ibm-granite/granite-4.1-8b-llmon-preview --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

Chat with the pipeline APIdocs
python
from transformers import pipeline

pipe = pipeline("text-generation", model="ibm-granite/granite-4.1-8b-llmon-preview", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])

Install Transformers

  • llama.cpp logollama.cppofficial · inference server

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
liodon-ai/granite-4.1-8b-llmon-preview-FP8SafetensorsFP8——
liodon-ai/granite-4.1-8b-llmon-preview-ONNXONNX———

About granite-4.1-8b-llmon-preview

Model Summary: Granite-4.1-8B-LLMON-preview is an 8B-parameter instruct model fine-tuned from Granite-4.1-8B-base to consume prompts in LLMON (LLM Object Notation) instead of a conventional chat template. LLMON wraps every part of a prompt (system policy, instructions, data, documents, tool definitions, and tool results) in an individually addressable block and adds an exec block that names which instruction to run, which inputs it operates on, and where the output goes. • Developers: Granite Team, IBM • HF Collection: Granite Experiments HF Collection • Other sizes: Granite-4.1-3B-LLMON-preview • Technical Blog: LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B • GitHub Repository: generative-computing/llmon • Visualization Demo: LLMON on Hugging Face Spaces • Release Date: November 12, 2026 • License: Apache 2.0 Supported Languages: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may fine-tune the model for languages beyond these. Intended use: The model is designed to follow general instructions and can serve as the foundation for AI assistants across diverse domains, including business applications, as well as for LLM agents equipped with tool-use capabilities. It is particularly suited to settings where a prompt mixes trusted instructions with untrusted material (retrieved documents, pasted content, or tool results) and the boundary between the two must be explicit.

Full model card on Hugging Face →

Other Granite 4.1 Llmon models

Whole family →
ibm-granite logo3.7BCommercial OK≈3.3 GB↓ 1.8K

Alternatives to granite-4.1-8b-llmon-preview

All alternatives →
ornith-ai logo

Ornith-1.0-9B

ornith-ai·Chat

≈6.8 GB

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

9B256K ctx MIT
818.9KJun 2026gguf
ornith-ai logo

Ornith-1.5-9B

ornith-ai·Chat

≈7.2 GB

Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.

9.7B256K ctx MIT
542.6KAug 2026ollama
Qwen logo

Qwen3-8B

Qwen·Chat

≈6.5 GB

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

8.2B40K ctx Apache 2.0
6.2MApr 2025ollama
ibm-granite logo

granite-4.2-8b

ibm-granite·Chat

≈7.0 GB

Granite is a family of open-source large language models developed by IBM, designed for enterprise and research use. Granite models are built to be versatile, safe, and efficient — covering a range of sizes and capabilities from compact edge-deployable models to large-scale reasoning systems.

8.8B128K ctx Apache 2.0
61.7KAug 2026ollama
ibm-granite logo

granite-4.1-8b

ibm-granite·Chat

≈7.0 GB

Model Summary: Granite-4.1-8B is a 8B parameter long-context instruct model finetuned from Granite-4.1-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.

8.8B128K ctx Apache 2.0
84.7KApr 2026ollama
IFM logo

K2-Horizon-7B

IFM·Chat

≈7.0 GB

K2-Horizon-7B is the medium dense member of the K2-Horizon family: a 7B-core decoder-only model with a 512K context window.

9B512K ctx Apache 2.0
31.2KSept 2026gguf

granite-4.1-8b-llmon-preview FAQ

How much VRAM does granite-4.1-8b-llmon-preview need?
About 7.0 GB at Q4_K_M with an 8K context. Q8_0 needs about 11 GB and full precision about 19 GB. Longer contexts need more memory for the KV cache.
Can granite-4.1-8b-llmon-preview run on the RTX 4060?
Yes. It fits at Q4_K_M (about 7.0 GB), at an estimated 28 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
Can I use granite-4.1-8b-llmon-preview 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 granite-4.1-8b-llmon-preview?
131,072 tokens (128K). The full window needs far more memory than an 8K context.
How do I run granite-4.1-8b-llmon-preview locally?
With vLLM: vllm serve ibm-granite/granite-4.1-8b-llmon-preview.

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.