utStability AI · Downloadable
japanese-stablelm-instruct-alpha-7b-v2
Generates text for conversations and writing.
- Source listed
- Sep 26, 2023
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
YOUR MEMORY BUDGET
Local AI models for 8GB VRAM.
Explore models by theoretical weight storage. This shortlist covers available downloadable language models with a known or name-derived parameter count.
6 GBleft for weights at 4-bit
8 GB budget − 2 GB reserve
8 GB budget − 2 GB reserve
The reserve is your assumption, not a measured overhead allowance. The default 2 GB may be too little for your runtime or context length. Results are not confirmed fits and have no verified speed rating. Weight estimates use decimal GB and do not include quantization overhead. For timed results on one 12GB machine, see measured speeds.
852 models within the weight budget
Largest parameter count first · not a quality rankingStability AI · Downloadable
japanese-stablelm-instruct-beta-7b
Generates text for conversations and writing.
- Source listed
- Oct 30, 2023
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- llama2
Stability AI · Downloadable
japanese-stablelm-instruct-gamma-7b
Generates text for conversations and writing.
- Source listed
- Oct 16, 2023
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Stability AI · Downloadable
japanese-stablelm-instruct-ja_vocab-beta-7b
Generates text for conversations and writing.
- Source listed
- Oct 30, 2023
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- llama2
Stability AI · Downloadable
StableBeluga-7B
Generates text for conversations and writing.
- Source listed
- Jul 27, 2023
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- Not disclosed
Stability AI · Downloadable
stablelm-base-alpha-7b
Generates text for conversations and writing.
- Source listed
- Apr 11, 2023
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- cc-by-sa-4.0
Stability AI · Downloadable
stablelm-base-alpha-7b-v2
Generates text for conversations and writing.
- Source listed
- Aug 4, 2023
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- cc-by-sa-4.0
Stability AI · Downloadable
stablelm-tuned-alpha-7b
Generates text for conversations and writing.
- Source listed
- Apr 19, 2023
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- cc-by-nc-sa-4.0
StepFun · Downloadable
StepFun-Formalizer-7B
Generates text for conversations and writing.
- Source listed
- Aug 19, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Tencent · Downloadable
HiLS-Attention-7B
Generates text for conversations and writing.
- Source listed
- Jul 9, 2026
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Tencent · Downloadable
Hunyuan-7B-Instruct
Generates text for conversations and writing.
- Source listed
- Jul 30, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- Not disclosed
Tencent · Downloadable
Hunyuan-7B-Instruct-0124
Generates text for conversations and writing.
- Source listed
- Jan 24, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- other
Tencent · Downloadable
Hunyuan-7B-Pretrain
Generates text for conversations and writing.
- Source listed
- Jul 28, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- Not disclosed
Tencent · Downloadable
Hunyuan-7B-Pretrain-0124
Generates text for conversations and writing.
- Source listed
- Jan 24, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- other
Tencent · Downloadable
WeDLM-7B-Base
Generates text for conversations and writing.
- Source listed
- Dec 25, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Tencent · Downloadable
WeDLM-7B-Instruct
Generates text for conversations and writing.
- Source listed
- Dec 25, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Xiaomi MiMo · Downloadable
MiMo-7B-Base
Generates text for conversations and writing.
- Source listed
- Apr 29, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
Xiaomi MiMo · Downloadable
MiMo-7B-RL
Generates text for conversations and writing.
- Source listed
- Apr 29, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
Xiaomi MiMo · Downloadable
MiMo-7B-RL-0530
Generates text for conversations and writing.
- Source listed
- May 30, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
Xiaomi MiMo · Downloadable
MiMo-7B-RL-Zero
Generates text for conversations and writing.
- Source listed
- Apr 29, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
Xiaomi MiMo · Downloadable
MiMo-7B-SFT
Generates text for conversations and writing.
- Source listed
- Apr 29, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
Xiaomi MiMo · Downloadable
MiMo-Embodied-7B
Understands text and images and responds in text.
- Source listed
- Nov 19, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
Xiaomi MiMo · Downloadable
MiMo-VL-7B-RL
Understands text and images and responds in text.
- Source listed
- May 30, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
Xiaomi MiMo · Downloadable
MiMo-VL-7B-RL-2508
Understands text and images and responds in text.
- Source listed
- Aug 7, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
What changes with a 8GB budget?
With 2 GB set aside, 6 GB remains for weights. At 4-bit that allows up to 12 billion parameters in the theoretical calculation. An 8-billion-parameter model alone needs approximately 4 GB at this precision, before its conversation cache and runtime.
Why might a listed model still fail to load?
Its actual weight format may need more space, the runtime may not support its architecture, or the conversation cache may exceed your reserve. Vision models can also need space for image processing. Check the original model card and measure your exact setup before relying on it.
Read the memory guide and technical sources · Compare two models