Skip to content
Weights Not Walls
Menu

meta-models

Muse-Spark-Open-816B-A42B

Reviewedgated on the Hubaccepts images
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

15 independent results on 9 eval sets
  • 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

GPQA diamondRe-run by Epoch AI
  • 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

OTIS Mock AIME 2024-2025Re-run by Epoch AI
  • 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

SimpleQA VerifiedRe-run by Epoch AI
  • 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

APEX-AgentsReported

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

ARC-AGIReported

Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: claude-fable-5_max, 98.5% (Anthropic). All 318 results

ARC-AGI-2Reported

Epoch's name: Muse-Spark-Open-816B-A42B. Best closed model on this set: gpt-6-astra_max, 95.0% (OpenAI). All 299 results

CritPtReported

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

file sizes read from the Hub 19 Nov 2026

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.

FormatSizeMemory neededGet it
UD-IQ1_S163.6 GBfile size, 5 parts164.9 GB163.6 + 0.86 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ1_S
Download
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_M194.6 GBfile size, 6 parts195.9 GB194.6 + 0.86 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ1_M
Download
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_XXS210.1 GBfile size, 6 parts211.4 GB210.1 + 0.86 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ2_XXS
Download
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_S256.6 GBfile size, 7 parts257.9 GB256.6 + 0.86 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ2_S
Download
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_XL289.9 GBfile size, 8 parts291.2 GB289.9 + 0.86 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-Q2_K_XL
Download
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_XXS317.0 GBfile size, 8 parts318.3 GB317.0 + 0.86 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-IQ3_XXS
Download
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_XL373.9 GBfile size, 10 parts375.3 GB373.9 + 0.86 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-Q3_K_XL
Download
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_XL470.8 GBfile size, 12 parts472.1 GB470.8 + 0.86 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF:UD-Q4_K_XL
Download
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

FormatSizeMemory neededRepo
MLXmlx-community/Muse-Spark-Open-816B-A42B-oQ3e346.0 GBfile size347.3 GB346.0 + 0.86 + 0.50Download page
MLX 4bitmlx-community/Muse-Spark-Open-816B-A42B-4bit496.2 GBfile size497.6 GB496.2 + 0.86 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights1531.4 GBfile size1532.8 GB1531.4 + 0.86 + 0.50
hf download meta-models/Muse-Spark-Open-816B-A42B --local-dir Muse-Spark-Open-816B-A42B
Other conversions (11; sizes not read)

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

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

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.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
BaseTen$1.25$4.251Mfp41770.5 s100.0%yesno
Fireworks$1.25$4.251Mnot given1390.3 s100.0%yesyes
Modal$1.25$4.25977knot given2120.5 s100.0%yesyes
Nebius$1.25$4.251Mfp41450.6 s96.8%yesyes
Together$1.25$4.251Mnot given1290.4 s100.0%yesyes

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

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

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.