- Size
- 822B parameters, 42.0B active (from the repo name)counted from the safetensors header on the Hub
- Licence
- custom, read it, Muse Model LicenseOur 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
- 15 Sep 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)MuseSparkForConditionalGeneration
- On Hugging Face
- meta-models/Muse-Spark-Open-816B-A42B14k downloads in the last 30 days, 761 likes
Scores
- effort xhigh31.7%±7.415 Oct 2026, Epoch AI
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: claude-fable-5-2_max, 100.0% (Anthropic). All 83 results
- effort xhigh69.8%±2.715 Oct 2026, Epoch AI
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: claude-fable-5-2_max, 95.1% (Anthropic). All 127 results
- effort xhigh88.6%±1.915 Oct 2026, log
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- effort xhigh98.1%±1.315 Oct 2026, log
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- effort xhigh56.6%±1.615 Oct 2026, log
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: claude-fable-5-2_max, 94.0% (Anthropic). All 105 results
- effort unknown33.4%via Epoch AI (error bar left out)
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: gemini-4-carbon_unknown, 84.2% (Google DeepMind). All 66 results
- effort xhigh89.0%arcprize.org
- effort high88.5%arcprize.org
- effort medium77.7%arcprize.org
- effort low58.5%arcprize.org
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: claude-fable-5_max, 98.5% (Anthropic). All 318 results
- effort xhigh57.5%via Epoch AI
- effort high47.5%via Epoch AI
- effort medium27.5%via Epoch AI
- effort low12.2%via Epoch AI
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: gpt-6-astra_max, 95.0% (OpenAI). All 299 results
- effort xhigh14.9%via Epoch AI
Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 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: 0.86 GB, worked out from the model's config (mlx-community/Muse-Spark-Open-816B-A42B-4bit), 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/Muse-Spark-Open-816B-A42B-GGUF (converted by unsloth), 10k 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 (3.8 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| UD-IQ1_S | 163.6 GBfile size, 5 parts | 164.9 GB163.6 + 0.86 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ1_SDownload hf download unsloth/Muse-Spark-Open-816B-A42B-GGUF --include "UD-IQ1_S/Muse-Spark-Open-816B-A42B-UD-IQ1_S-*-of-00005.gguf" --local-dir Muse-Spark-Open-816B-A42B-GGUF |
| UD-IQ1_M | 194.6 GBfile size, 6 parts | 195.9 GB194.6 + 0.86 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ1_MDownload hf download unsloth/Muse-Spark-Open-816B-A42B-GGUF --include "UD-IQ1_M/Muse-Spark-Open-816B-A42B-UD-IQ1_M-*-of-00006.gguf" --local-dir Muse-Spark-Open-816B-A42B-GGUF |
| UD-IQ2_XXS | 210.1 GBfile size, 6 parts | 211.4 GB210.1 + 0.86 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ2_XXSDownload hf download unsloth/Muse-Spark-Open-816B-A42B-GGUF --include "UD-IQ2_XXS/Muse-Spark-Open-816B-A42B-UD-IQ2_XXS-*-of-00006.gguf" --local-dir Muse-Spark-Open-816B-A42B-GGUF |
| UD-IQ2_S | 256.6 GBfile size, 7 parts | 257.9 GB256.6 + 0.86 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ2_SDownload hf download unsloth/Muse-Spark-Open-816B-A42B-GGUF --include "UD-IQ2_S/Muse-Spark-Open-816B-A42B-UD-IQ2_S-*-of-00007.gguf" --local-dir Muse-Spark-Open-816B-A42B-GGUF |
| UD-Q2_K_XL | 289.9 GBfile size, 8 parts | 291.2 GB289.9 + 0.86 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-Q2_K_XLDownload hf download unsloth/Muse-Spark-Open-816B-A42B-GGUF --include "UD-Q2_K_XL/Muse-Spark-Open-816B-A42B-UD-Q2_K_XL-*-of-00008.gguf" --local-dir Muse-Spark-Open-816B-A42B-GGUF |
| UD-IQ3_XXS | 317.0 GBfile size, 8 parts | 318.3 GB317.0 + 0.86 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ3_XXSDownload hf download unsloth/Muse-Spark-Open-816B-A42B-GGUF --include "UD-IQ3_XXS/Muse-Spark-Open-816B-A42B-UD-IQ3_XXS-*-of-00008.gguf" --local-dir Muse-Spark-Open-816B-A42B-GGUF |
| UD-Q3_K_XL | 373.9 GBfile size, 10 parts | 375.3 GB373.9 + 0.86 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-Q3_K_XLDownload hf download unsloth/Muse-Spark-Open-816B-A42B-GGUF --include "UD-Q3_K_XL/Muse-Spark-Open-816B-A42B-UD-Q3_K_XL-*-of-00010.gguf" --local-dir Muse-Spark-Open-816B-A42B-GGUF |
| UD-Q4_K_XL | 470.8 GBfile size, 12 parts | 472.1 GB470.8 + 0.86 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-Q4_K_XLDownload hf download unsloth/Muse-Spark-Open-816B-A42B-GGUF --include "UD-Q4_K_XL/Muse-Spark-Open-816B-A42B-UD-Q4_K_XL-*-of-00012.gguf" --local-dir Muse-Spark-Open-816B-A42B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXmlx-community/Muse-Spark-Open-816B-A42B-oQ3e | 346.0 GBfile size | 347.3 GB346.0 + 0.86 + 0.50 | Download page |
| MLX 4bitmlx-community/Muse-Spark-Open-816B-A42B-4bit | 496.2 GBfile size | 497.6 GB496.2 + 0.86 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 1531.4 GBfile size | 1532.8 GB1531.4 + 0.86 + 0.50 |
hf download meta-models/Muse-Spark-Open-816B-A42B --local-dir Muse-Spark-Open-816B-A42BOther conversions (11; sizes not read)
- meta-models/Muse-Spark-Open-816B-A42B-NVFP4 NVFP4, by the maker, 56k downloads
- amd/Muse-Spark-Open-816B-A42B-Quark-MXFP4 Other, mxfp4, 12k downloads
- unsloth/Muse-Spark-Open-816B-A42B-NVFP4 NVFP4, 2.3k downloads
- amd/Muse-Spark-Open-816B-A42B-Quark-PTPC-FP8 FP8, 1.1k downloads
- intel-ai/Muse-Spark-Open-816B-A42B-MXFP4 Other, mxfp4, 392 downloads
- intel-ai/Muse-Spark-Open-816B-A42B-INT4 Other, int4, 375 downloads
- RedHatAI/Muse-Spark-Open-816B-A42B-MXFP4xFP8 FP8, 195 downloads
- ml-resources/Muse-Spark-Open-816B-A42B-NVFP4 NVFP4, 150 downloads
- vcruz305/Muse-Spark-Open-816B-A42B-EXL3-SAGE-1.13bpw EXL3, 148 downloads
- HawkBearPig/Muse-Spark-Open-816B-A42B-EXL3-4bit-mixed EXL3, 4bit, 38 downloads
- vcruz305/Muse-Spark-Open-816B-A42B-EXL3-SAGE-2.25bpw EXL3, 2 downloads
The Hub tags 25 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
5 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 |
|---|---|---|---|---|---|---|---|---|---|
| BaseTen | $1.25 | $4.25 | 1M | fp4 | 177 | 0.5 s | 100.0% | yes | no |
| Fireworks | $1.25 | $4.25 | 1M | not given | 139 | 0.3 s | 100.0% | yes | yes |
| Modal | $1.25 | $4.25 | 977k | not given | 212 | 0.5 s | 100.0% | yes | yes |
| Nebius | $1.25 | $4.25 | 1M | fp4 | 145 | 0.6 s | 96.8% | yes | yes |
| Together | $1.25 | $4.25 | 1M | not given | 129 | 0.4 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": "meta-models/Muse-Spark-Open-816B-A42B:baseten", "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.
- nvidia/Muse-Spark-Open-816B-A42B-DFlash22.5kUnreviewed
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.