DiscoPOP-zephyr-7b-gemma
DiscoPOP-zephyr-7b-gemma is an open-weight language model from Sakana AI with 8.5B parameters. At 4-bit it needs about 9.8 GB of memory, so the smallest current device that fits it is the GeForce RTX 5060 Ti 16GB.
Overview
Includes room for an 8k context and runtime overhead. More context needs more memory.
Key information
- Lab
- Sakana AI
- Released
- 12 Jun 2024
- Parameters
- 8.5B
- Type
- Language
- Context
- 8,192 tokens
- License
- Gemma terms
- HF downloads, 30 days
- 94
- Repository
- SakanaAI/DiscoPOP-zephyr-7b-gemma
More from Sakana AI
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 9.8 GB |
| Q8 | 14.1 GB |
| BF16 | 22.9 GB |
| RTX 5060 Ti 16 GB | 16 GB usable |
| RTX 5090 32 GB | 32 GB usable |
| DGX Spark 128 GB | 108.8 GB usable |
| Mac Studio M5 Ultra 256 GB | 192 GB usable |
Single-device memory estimate. Pick a device to update the On your device column.
36 GB usable memory
| Format | Memory needed | On your device | Example hardware |
|---|---|---|---|
| 4-bit (Q4) | ≈ 9.8 GB | Fits 27% | GeForce RTX 5060 Ti 16GB16 GB memory |
| 8-bit (Q8) | ≈ 14.1 GB | Fits 39% | GeForce RTX 5060 Ti 16GB16 GB memory |
| 16-bit (BF16) | ≈ 22.9 GB | Fits 64% | Radeon AI PRO R970032 GB memory |
Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.
Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.
Where to run it
With GGUF
Choose a file for llama.cpp or a compatible app.
bartowski/DiscoPOP-zephyr-7b-gemma-GGUFFind compatible hardwareThrough an API
No hosted API found.
llama-cli -hf bartowski/DiscoPOP-zephyr-7b-gemma-GGUF \
-c 8192 -p "Explain how a transformer works."Example commands built from the repository ids above. They need a working install of llama.cpp. We have not run them; check each repository for available files.
More about this model
Frequently asked questions
How much memory does DiscoPOP-zephyr-7b-gemma need? At an 8k context, about 9.8 GB at 4-bit, 14.1 GB at 8-bit and 22.9 GB at 16-bit (BF16). A longer context needs more.
Can I run DiscoPOP-zephyr-7b-gemma on a Mac? The smallest current Mac that fits the 4-bit estimate of 9.8 GB is the Mac mini M5 Pro (24GB). We have not found a trusted MLX build yet, but a GGUF build is available.
Does the full context fit? DiscoPOP-zephyr-7b-gemma supports up to 8,192 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.
What does it cost through an API? We did not find a hosted API for this model.
License in plain English
Gemma terms. These are Google's Gemma terms of use. They allow use and distribution with conditions, including a prohibited use policy. This summary is not legal advice.
OMHQ RigBench
Not yet tested. We show no speed or quality score without a measurement.
Revision history and sources
Last updated . Sources:Hugging Face model card, GGUF repository.