- Size
- 594B parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: unsloth/Inkling-2-Small-GGUF
- Licence
- custom, read it, Apache License 2.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 4 Nov 2026the date the repo was created
- Context length
- 1M tokensas an API provider reports it
- Kind
- Base model (no base model declared on the Hub)Inkling2ForConditionalGeneration
- On Hugging Face
- thinkingmachines/Inkling-2-Small37k downloads in the last 30 days, 560 likes
Scores
- effort unknown46.8%via Epoch AI (error bar left out)
Epoch's name: inkling-2-small. Best closed model on this set: gemini-4-carbon_unknown, 84.2% (Google DeepMind). All 66 results
- effort xhigh96.5%arcprize.org
Epoch's name: inkling-2-small. Best closed model on this set: claude-fable-5_max, 98.5% (Anthropic). All 318 results
- effort xhigh81.7%via Epoch AI
Epoch's name: inkling-2-small. Best closed model on this set: gpt-6-astra_max, 95.0% (OpenAI). All 299 results
- effort xhigh; Harness: proximus25.1%frontierswe.com
Epoch's name: inkling-2-small. Best closed model on this set: claude-fable-5-2_max, 69.9% (Anthropic). All 25 results
- effort xhigh43.6%surgehq.ai
Epoch's name: inkling-2-small. Best closed model on this set: gemini-4-carbon_high, 56.4% (Google DeepMind). All 19 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.5 GB, worked out from the model's config (thinkingmachines/Inkling-2-Small), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
unsloth/Inkling-2-Small-GGUF (converted by unsloth), 6.4k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-F16.gguf (0.61 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| UD-IQ1_S | 159.9 GBfile size, 5 parts | 161.9 GB159.9 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:UD-IQ1_SDownload hf download unsloth/Inkling-2-Small-GGUF --include "UD-IQ1_S/Inkling-2-Small-UD-IQ1_S-*-of-00005.gguf" --local-dir Inkling-2-Small-GGUF |
| UD-IQ1_M | 166.3 GBfile size, 5 parts | 168.3 GB166.3 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:UD-IQ1_MDownload hf download unsloth/Inkling-2-Small-GGUF --include "UD-IQ1_M/Inkling-2-Small-UD-IQ1_M-*-of-00005.gguf" --local-dir Inkling-2-Small-GGUF |
| UD-IQ2_XXS | 177.5 GBfile size, 5 parts | 179.5 GB177.5 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:UD-IQ2_XXSDownload hf download unsloth/Inkling-2-Small-GGUF --include "UD-IQ2_XXS/Inkling-2-Small-UD-IQ2_XXS-*-of-00005.gguf" --local-dir Inkling-2-Small-GGUF |
| UD-Q2_K_XL | 190.9 GBfile size, 6 parts | 192.9 GB190.9 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:UD-Q2_K_XLDownload hf download unsloth/Inkling-2-Small-GGUF --include "UD-Q2_K_XL/Inkling-2-Small-UD-Q2_K_XL-*-of-00006.gguf" --local-dir Inkling-2-Small-GGUF |
| UD-IQ3_XXS | 210.5 GBfile size, 6 parts | 212.5 GB210.5 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:UD-IQ3_XXSDownload hf download unsloth/Inkling-2-Small-GGUF --include "UD-IQ3_XXS/Inkling-2-Small-UD-IQ3_XXS-*-of-00006.gguf" --local-dir Inkling-2-Small-GGUF |
| UD-Q3_K_XL | 265.5 GBfile size, 7 parts | 267.5 GB265.5 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:UD-Q3_K_XLDownload hf download unsloth/Inkling-2-Small-GGUF --include "UD-Q3_K_XL/Inkling-2-Small-UD-Q3_K_XL-*-of-00007.gguf" --local-dir Inkling-2-Small-GGUF |
| UD-Q4_K_XL | 329.8 GBfile size, 9 parts | 331.8 GB329.8 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:UD-Q4_K_XLDownload hf download unsloth/Inkling-2-Small-GGUF --include "UD-Q4_K_XL/Inkling-2-Small-UD-Q4_K_XL-*-of-00009.gguf" --local-dir Inkling-2-Small-GGUF |
| UD-Q8_K_XL | 360.0 GBfile size, 9 parts | 362.0 GB360.0 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:UD-Q8_K_XLDownload hf download unsloth/Inkling-2-Small-GGUF --include "UD-Q8_K_XL/Inkling-2-Small-UD-Q8_K_XL-*-of-00009.gguf" --local-dir Inkling-2-Small-GGUF |
| BF16 | 451.1 GBfile size, 11 parts | 453.1 GB451.1 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Inkling-2-Small-GGUF:BF16Download hf download unsloth/Inkling-2-Small-GGUF --include "BF16/Inkling-2-Small-BF16-*-of-00011.gguf" --local-dir Inkling-2-Small-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXmlx-community/Inkling-2-Small-oQ4e | 318.0 GBfile size | 320.0 GB318.0 + 1.5 + 0.50 | Download page |
| MLX 4bitmlx-community/Inkling-2-Small-4bit | 354.6 GBfile size | 356.6 GB354.6 + 1.5 + 0.50 | Download page |
Original weights
The maker's own weights are packed into integer tensors, so the safetensors header gives no size we can trust; the repo lists the real file sizes.
hf download thinkingmachines/Inkling-2-Small --local-dir Inkling-2-SmallOther conversions (9; sizes not read)
- Baekpica/Inkling-2-Small-VQ-GGUF GGUF, 2.4k downloads; sizes not used: every file is far too small for this model; the repo may be tagged wrongly or hold only part of it
- 0xSero/Inkling-2-Small-EXL3-4bpw EXL3, 301 downloads
- mel-bw/Inkling-2-Small-EXL3-3.17bpw EXL3, 233 downloads
- 0xSero/Inkling-2-Small-EXL3-3.48bpw EXL3, 137 downloads
- btbtyler09/Inkling-2-Small-NVFP4 NVFP4, 85 downloads
- Nidhal101/Inkling-2-Small-CLEER-k8 Other, 32 downloads
- OpensourceWTF/Inkling-2-Small-exl3 EXL3, 19 downloads
- Jon-Nielsen/Inkling-2-Small-NVFP4-CSF-FLARE-sm120-1M-vision NVFP4, 0 downloads
- gatilin/inkling-2-small-vision-encoder Other, 0 downloads
The Hub tags 21 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
6 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| PrimeIntellect | $0.15 | $0.50 | 1M | fp4 | 84 | 1.4 s | 99.8% | yes | yes |
| DeepInfra | $0.28 | $0.95 | 1M | fp4 | 182 | 0.6 s | 99.4% | yes | yes |
| Cloudflare | $0.30 | $1.00 | 1M | not given | 237 | 1.0 s | 99.9% | yes | yes |
| Modal | $0.30 | $1.00 | 1M | nvfp4 | 198 | 0.8 s | 100.0% | yes | yes |
| Nebius | $0.30 | $1.00 | 1M | fp4 | 176 | 0.3 s | 97.3% | yes | yes |
| Together | $0.30 | $1.00 | 1M | not given | 157 | 0.5 s | 100.0% | yes | yes |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "thinkingmachines/Inkling-2-Small:primeintellect", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- migtissera/Tess-4.5-594B-A17B284Unreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.