266
Parakeet-TDT-0.6b-V2
Transcribe audio to text with timestamps
Bertrand Chevrier
kramp
AI & ML interests
text 2 speech, ai for music writting
Recent Activity
liked
a Space
1 day ago
nvidia/parakeet-tdt-0.6b-v2
liked
a model
4 days ago
nari-labs/Dia-1.6B
Organizations
kramp's activity
liked
a
Space
1 day ago
liked
a
model
4 days ago
reacted to
wolfram's
post with 👍
4 days ago
Post
6979
Finally finished my extensive **Qwen 3 evaluations** across a range of formats and quantisations, focusing on **MMLU-Pro** (Computer Science).
A few take-aways stood out - especially for those interested in local deployment and performance trade-offs:
1️⃣ **Qwen3-235B-A22B** (via Fireworks API) tops the table at **83.66%** with ~55 tok/s.
2️⃣ But the **30B-A3B Unsloth** quant delivered **82.20%** while running locally at ~45 tok/s and with zero API spend.
3️⃣ The same Unsloth build is ~5x faster than Qwen's **Qwen3-32B**, which scores **82.20%** as well yet crawls at <10 tok/s.
4️⃣ On Apple silicon, the **30B MLX** port hits **79.51%** while sustaining ~64 tok/s - arguably today's best speed/quality trade-off for Mac setups.
5️⃣ The **0.6B** micro-model races above 180 tok/s but tops out at **37.56%** - that's why it's not even on the graph (50 % performance cut-off).
All local runs were done with LM Studio on an M4 MacBook Pro, using Qwen's official recommended settings.
**Conclusion:** Quantised 30B models now get you ~98 % of frontier-class accuracy - at a fraction of the latency, cost, and energy. For most local RAG or agent workloads, they're not just good enough - they're the new default.
Well done, Qwen - you really whipped the llama's ass! And to OpenAI: for your upcoming open model, please make it MoE, with toggleable reasoning, and release it in many sizes. *This* is the future!
A few take-aways stood out - especially for those interested in local deployment and performance trade-offs:
1️⃣ **Qwen3-235B-A22B** (via Fireworks API) tops the table at **83.66%** with ~55 tok/s.
2️⃣ But the **30B-A3B Unsloth** quant delivered **82.20%** while running locally at ~45 tok/s and with zero API spend.
3️⃣ The same Unsloth build is ~5x faster than Qwen's **Qwen3-32B**, which scores **82.20%** as well yet crawls at <10 tok/s.
4️⃣ On Apple silicon, the **30B MLX** port hits **79.51%** while sustaining ~64 tok/s - arguably today's best speed/quality trade-off for Mac setups.
5️⃣ The **0.6B** micro-model races above 180 tok/s but tops out at **37.56%** - that's why it's not even on the graph (50 % performance cut-off).
All local runs were done with LM Studio on an M4 MacBook Pro, using Qwen's official recommended settings.
**Conclusion:** Quantised 30B models now get you ~98 % of frontier-class accuracy - at a fraction of the latency, cost, and energy. For most local RAG or agent workloads, they're not just good enough - they're the new default.
Well done, Qwen - you really whipped the llama's ass! And to OpenAI: for your upcoming open model, please make it MoE, with toggleable reasoning, and release it in many sizes. *This* is the future!
- 4 replies
liked
a
dataset
7 days ago
updated
a
collection
9 days ago
liked
a
model
13 days ago
liked
a
model
15 days ago
liked
a
Space
16 days ago
upvoted
an
article
18 days ago
Article
Tiny Agents: a MCP-powered agent in 50 lines of code
•
231
liked
a
Space
19 days ago
liked
a
Space
20 days ago
upvoted
an
article
27 days ago
Article
Cohere on Hugging Face Inference Providers 🔥
•
124
liked
a
Space
28 days ago
upvoted
an
article
29 days ago
Article
Hugging Face to sell open-source robots thanks to Pollen Robotics acquisition 🤖
•
45
Async active filters on HomePage laggy or broken
3
#67 opened about 1 month ago
by
Aurelien-Morgan
reacted to
enzostvs's
post with 🔥
about 1 month ago
Post
22761
(not available anymore)
Looking for a logo idea 👀 ?
I made a new cool space https://huggingface.co/spaces/enzostvs/Logo.Ai to help you design a great logo in seconds!
Here are some examples of what you can do, feel free to share yours too! 🚀
Looking for a logo idea 👀 ?
I made a new cool space https://huggingface.co/spaces/enzostvs/Logo.Ai to help you design a great logo in seconds!
Here are some examples of what you can do, feel free to share yours too! 🚀
- 6 replies
liked
a
Space
about 1 month ago
liked
a
model
about 1 month ago
