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.

thinkingmachines logo

Inkling-2-Small

thinkingmachines·Instruct·released 4 Nov 2026

Apache 2.0383BMoE1M ctx ≈229 GB
Your GPU
ollama run inkling-2-small
All 2 runners ↓

Inkling 2 Small is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

How much VRAM does Inkling-2-Small need?

At Q4_K_M Inkling-2-Small needs about 229 GB with an 8K context (229 GB at Q4, 751 GB at full precision). Pick your GPU to see what fits and how fast it runs.

--vram
any
--gpus
--quant

Needs: ≈229 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)

Quantisation8K16K32K64K128K1M
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 loss117 GB est.1.5 GB≈125 GB
Q3_K_MNoticeable lossSmall, some quality lossNoticeable loss174 GB est.1.5 GB≈185 GB
Q4_K_MrecommendedSmall lossRecommended default for local useSmall loss216 GB est.1.5 GB≈229 GB
Q5_K_MNear-losslessNear-lossless for most tasksNear-lossless254 GB est.1.5 GB≈268 GB
Q6_KNear-losslessPractically losslessNear-lossless294 GB est.1.5 GB≈311 GB
Q8_0LosslessLossless in practice, twice the size of Q4Lossless379 GB est.1.5 GB≈400 GB
FP16 / BF16LosslessFull precision, as releasedLossless451 GB file1.5 GB≈476 GB

Estimates for 8K tokens of context: weights + KV cache + runtime overhead. All experts stay in memory, but only the active ones are read per token. 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 ≈229 GB(216 GB weights + 1.5 GB KV cache + 11 GB overhead). Pick a GPU above to see how much context fits.

01002003004005001K2K4K8K16K32K64K128K256K512K1MGB

Weights + overheadKV cache

Can the Apple M3 Ultra (512 GB) run Inkling-2-Small? →

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 Inkling-2-Small

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 Inkling-2-Small locally

--quantQ4_K_Mdefault; pick your GPU to tailor itunsloth/Inkling-2-Small-GGUF

From the Ollama librarydocs
ollama run inkling-2-small

The library build picks its own default quantisation.

UD-Q4_K_XL straight from Hugging Facedocs
ollama run hf.co/unsloth/Inkling-2-Small-GGUF:UD-Q4_K_XL

Install Ollama

Ask about an imagedocs
python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="thinkingmachines/Inkling-2-Small", dtype="auto", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])

Install Transformers

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
btbtyler09/Inkling-2-Small-NVFP4SafetensorsNVFP4—80
Jon-Nielsen/Inkling-2-Small-NVFP4-CSF-FLARE-sm120-1M-visionSafetensorsNVFP4——
unsloth/Inkling-2-Small-GGUFGGUFUD-IQ1_S172 GB6K
unsloth/Inkling-2-Small-GGUFGGUFUD-IQ1_M179 GB6K
unsloth/Inkling-2-Small-GGUFGGUFUD-IQ2_XXS191 GB6K
unsloth/Inkling-2-Small-GGUFGGUFUD-Q2_K_XL205 GB6K
unsloth/Inkling-2-Small-GGUFGGUFUD-IQ3_XXS226 GB6K
unsloth/Inkling-2-Small-GGUFGGUFUD-Q3_K_XL285 GB6K
unsloth/Inkling-2-Small-GGUFGGUFUD-Q4_K_XL354 GB6K
unsloth/Inkling-2-Small-GGUFGGUFUD-Q8_K_XL387 GB6K

About Inkling-2-Small

Inkling 2 Small is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and visual tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers. Languages: English, with general multilingual capabilities across other languages. Try Inkling 2 Small on the Tinker Playground or access via API using the Tinker Cookbook. To fine-tune Inkling 2 Small with Tinker, also install the tml-renderers package. Inkling 2 Small supports local inference using: • SGLang (recipe) • vLLM (recipe) • TokenSpeed (recipe) • Unsloth (recipe) Inkling 2 Small can also be post-trained with: • Miles • SkyRL • Snowflake Cortex Training API access is also available through third party inference providers, including: • NVIDIA • Fireworks • Together • Baseten • Nebius • Modal • Cloudflare The model is distributed in two checkpoint formats.

Full model card on Hugging Face →

Alternatives to Inkling-2-Small

All alternatives →
zai-org logo

GLM-5.3-Flash

zai-org·Vision

≈213 GB

👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.

321BA18.3B1M ctx MIT
6.4MAug 2026ollama
Qwen logo

Qwen3.5-397B-A17B

Qwen·Vision

≈241 GB

Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.

403BA17B256K ctx Apache 2.0
606.8KFeb 2026gguf
MiniMaxAI logo

MiniMax-M3

MiniMaxAI·Vision

≈255 GB

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

427B1M ctx minimax-community
147.1KJun 2026ollama
thinkingmachines logo

Inkling-Small

thinkingmachines·Vision

≈159 GB

Inkling-Small is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

266BA1.7B1M ctx Apache 2.0
860KJul 2026gguf
zai-org logo

GLM-5.3-Flash-BF16

zai-org·Vision

≈213 GB

👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.

321BA18.3B1M ctx MIT
20.1KAug 2026gguf
deepseek-ai logo

DeepSeek-V4-Flash-Vision-Exp

deepseek-ai·Vision

≈182 GB

We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.

305BA15.2B1M ctx MIT
28.6KAug 2026gguf

Inkling-2-Small FAQ

How much VRAM does Inkling-2-Small need?
About 229 GB at Q4_K_M with an 8K context. Q8_0 needs about 400 GB and full precision about 751 GB. Longer contexts need more memory for the KV cache.
Can Inkling-2-Small run on the Apple M3 Ultra (512 GB)?
Yes. It fits at Q6_K (about 311 GB), at an estimated 1.4 tokens/s.
Can I use Inkling-2-Small 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 Inkling-2-Small?
1,048,576 tokens (1M). The full window needs far more memory than an 8K context.
How do I run Inkling-2-Small with Ollama?
Run ollama run inkling-2-small in a terminal.

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.