HF
Hugging Face
Language model · United States ·Apr 2024

Zephyr 141B-A39B

Language Open (Restricted)
141B
Parameters

About Zephyr 141B-A39B

Zephyr 141B-A39B is an AI model developed by Hugging Face, in the language category, released in 2024, made available as an open-weights model with 141B params.

On this page you'll find Zephyr 141B-A39B's full specifications. Review provider pricing and benchmark scores below, or compare Zephyr 141B-A39B head-to-head with other language models.

→ More models by Hugging Face → All language models → AI benchmarks leaderboard

Links

Announcement ↗

Run Zephyr 141B-A39B locally — what to buy

Share this build ↗

Sized to what Zephyr 141B-A39B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
AMD Ryzen AI Max+ 395
Consumer GPU · ~$1,999
~2.5 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
Apple M2 Max 96GB
Apple · ~$3,300
~4.2 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
Apple M1 Ultra 128GB
Apple · ~$4,800
~8.3 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
2.5–3 tok/s
2 options →
Apple
4.2–8.3 tok/s
5 options →
Datacenter GPU
19.7–88.1 tok/s
6 options →

Community

Would you run Zephyr 141B-A39B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Zephyr 141B-A39B

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is Zephyr 141B-A39B? ▶

Zephyr 141B-A39B is an AI model developed by Hugging Face, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Zephyr 141B-A39B? ▶

Zephyr 141B-A39B was developed by Hugging Face and released in 2024.

Is Zephyr 141B-A39B open source or proprietary? ▶

Zephyr 141B-A39B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Zephyr 141B-A39B cost? ▶

Pricing for Zephyr 141B-A39B depends on the provider. See the providers table on this page for the latest API rates.

How does Zephyr 141B-A39B perform on benchmarks? ▶

Benchmark scores for Zephyr 141B-A39B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about Zephyr 141B-A39B?