AL
Almawave
Language model · Italy ·Oct 2025

Velvet 25B

Language Open Weights
25B
Parameters

About Velvet 25B

Velvet 25B is an AI model developed by Almawave, in the language category, released in 2025, made available as an open-weights model with 25B params. New-generation Almawave LLM covering 24 EU languages with long-document and reasoning focus..

On this page you'll find Velvet 25B's full specifications. Review provider pricing and benchmark scores below, or compare Velvet 25B head-to-head with other language models.

→ More models by Almawave → All language models → AI benchmarks leaderboard

Links

Announcement ↗

Run Velvet 25B locally — what to buy

Share this build ↗

Sized to what Velvet 25B 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 Radeon RX 7900 XT
Consumer GPU · ~$899
~44 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
AMD Radeon RX 7900 XTX
Consumer GPU · ~$999
~52.8 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5090
Consumer GPU · ~$1,999
~111.4 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
14.1–111.4 tok/s
10 options →
Apple
17.6–46.9 tok/s
17 options →
Datacenter GPU
47.5–120+ tok/s
13 options →

Community

Would you run Velvet 25B 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 Velvet 25B

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 Velvet 25B? ▶

New-generation Almawave LLM covering 24 EU languages with long-document and reasoning focus. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Velvet 25B? ▶

Velvet 25B was developed by Almawave and released in 2025.

Is Velvet 25B open source or proprietary? ▶

Velvet 25B 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 Velvet 25B cost? ▶

Pricing for Velvet 25B depends on the provider. See the providers table on this page for the latest API rates.

How does Velvet 25B perform on benchmarks? ▶

Benchmark scores for Velvet 25B 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 Velvet 25B?