- Size
- 952B parameterscounted from the safetensors header on the Hub
- 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
- 14 Jul 2026the date the repo was created
- Context length
- 512k tokensas an API provider reports it
- Kind
- Base model (no base model declared on the Hub)InklingForConditionalGeneration
- On Hugging Face
- thinkingmachines/Inkling1.4M downloads in the last 30 days, 1.9k likes
Scores
- effort xhigh21.0%±4.113 Oct 2026, log
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_max, 79.0% (Anthropic). All 166 results
- effort xhigh4.9%±3.46 Aug 2026, log
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_max, 100.0% (Anthropic). All 83 results
- effort xhigh33.3%±2.86 Aug 2026, log
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_max, 95.1% (Anthropic). All 127 results
- effort xhigh88.3%±1.95 Aug 2026, log
Epoch's name: Inkling. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- effort xhigh88.9%±3.95 Aug 2026, log
Epoch's name: Inkling. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- effort xhigh40.3%±1.627 Aug 2026, log
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_max, 94.0% (Anthropic). All 105 results
- default setting33.8%via Epoch AI (error bar left out)
Epoch's name: Inkling. Best closed model on this set: gemini-4-carbon_unknown, 84.2% (Google DeepMind). All 66 results
- default setting79.5%arcprize.org
Epoch's name: Inkling. Best closed model on this set: claude-fable-5_max, 98.5% (Anthropic). All 318 results
- default setting36.5%via Epoch AI
Epoch's name: Inkling. Best closed model on this set: gpt-6-astra_max, 95.0% (OpenAI). All 299 results
- effort xhigh5.4%via Epoch AI
Epoch's name: Inkling. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- effort xhigh87.5%conceptualreasoning.ai
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- Harness: mini-swe-agent; Reasoning effort: 0.9914.0%cognition.com
Epoch's name: Inkling. Best closed model on this set: claude-opus-5-5_medium, 54.6% (Anthropic). All 46 results
- effort xhigh; Harness: proximus4.1%frontierswe.com
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_max, 69.9% (Anthropic). All 25 results
- effort xhigh37.6%33.2 to 42.0conceptualreasoning.ai
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- default setting0.0%vals.ai
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-1_max, 100.0% (Anthropic). All 85 results
- default setting50.0%lmcouncil.ai
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_unknown, 94.9% (Anthropic). All 125 results
- effort high32.3%±0.0htihle.github.io
Epoch's name: Inkling. Best closed model on this set: gpt-6-astra_promax, 93.6% (OpenAI). All 173 results
- effort xhigh; Agent: opencode; Reasoning effort: xhigh4.4%htihle.github.io
Epoch's name: Inkling. Best closed model on this set: claude-fable-5-2_xhigh, 65.3% (Anthropic). All 27 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: 2.1 GB, worked out from the model's config (thinkingmachines/Inkling), 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-GGUF (converted by unsloth), 70k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-BF16.gguf (0.17 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| UD-IQ1_S | 251.6 GBfile size, 7 parts | 254.2 GB251.6 + 2.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/inkling-GGUF:UD-IQ1_SDownload hf download unsloth/inkling-GGUF --include "UD-IQ1_S/inkling-UD-IQ1_S-*-of-00007.gguf" --local-dir inkling-GGUF |
| UD-IQ1_M | 265.5 GBfile size, 7 parts | 268.0 GB265.5 + 2.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/inkling-GGUF:UD-IQ1_MDownload hf download unsloth/inkling-GGUF --include "UD-IQ1_M/inkling-UD-IQ1_M-*-of-00007.gguf" --local-dir inkling-GGUF |
| UD-Q2_K_XL | 295.5 GBfile size, 8 parts | 298.1 GB295.5 + 2.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/inkling-GGUF:UD-Q2_K_XLDownload hf download unsloth/inkling-GGUF --include "UD-Q2_K_XL/inkling-UD-Q2_K_XL-*-of-00008.gguf" --local-dir inkling-GGUF |
| UD-Q3_K_XL | 403.1 GBfile size, 10 parts | 405.6 GB403.1 + 2.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/inkling-GGUF:UD-Q3_K_XLDownload hf download unsloth/inkling-GGUF --include "UD-Q3_K_XL/inkling-UD-Q3_K_XL-*-of-00010.gguf" --local-dir inkling-GGUF |
| UD-Q4_K_XL | 546.7 GBfile size, 14 parts | 549.3 GB546.7 + 2.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/inkling-GGUF:UD-Q4_K_XLDownload hf download unsloth/inkling-GGUF --include "UD-Q4_K_XL/inkling-UD-Q4_K_XL-*-of-00014.gguf" --local-dir inkling-GGUF |
| Q8_0 | 797.9 GBfile size, 19 parts | 800.5 GB797.9 + 2.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/inkling-GGUF:Q8_0Download hf download unsloth/inkling-GGUF --include "Q8_0/inkling-GGUF-Q8_0-*-of-00019.gguf" --local-dir inkling-GGUF |
| BF16 | 1764.2 GBfile size, 41 parts | 1766.7 GB1764.2 + 2.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/inkling-GGUF:BF16Download hf download unsloth/inkling-GGUF --include "BF16/inkling-GGUF-BF16-*-of-00041.gguf" --local-dir inkling-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXavlp12/Inkling-975B-Alis-MLX-Dynamic-3.7bpw | 408.7 GBfile size | 411.2 GB408.7 + 2.1 + 0.50 | Download page |
| MLX 4bitpipenetwork/Inkling-MLX-4bit | 496.3 GBfile size | 498.9 GB496.3 + 2.1 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 1773.9 GBfile size | 1776.5 GB1773.9 + 2.1 + 0.50 |
hf download thinkingmachines/Inkling --local-dir InklingOther conversions (9; sizes not read)
- thinkingmachines/Inkling-NVFP4 NVFP4, by the maker, 26k downloads
- sabrewing-engine/Inkling-colibri-int4 Other, int4, 1.2k downloads
- lightseekorg/Inkling-MXFP4 Other, mxfp4, 782 downloads
- RedHatAI/Inkling-NVFP4-FP8-BLOCK NVFP4, 285 downloads
- thunquant/Inkling-NVFP4 NVFP4, 239 downloads
- winterthurquants/Inkling-NVFP4 NVFP4, 235 downloads
- RedHatAI/Inkling-FP8-dynamic FP8, 230 downloads
- RedHatAI/Inkling-FP8-block FP8, 205 downloads
- biosai-hf/Inkling-MXFP4 Other, mxfp4, 152 downloads
The Hub tags 48 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
2 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 |
|---|---|---|---|---|---|---|---|---|---|
| deepinfra | $0.95 | $4.05 | 512k | not given | 130 | 0.4 s | ? | yes | yes |
| Together | $1.00 | $4.05 | 512k | not given | 118 | 0.2 s | 99.9% | yes | no |
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:deepinfra", "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.
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.