berkeley-nest_starling-lm-7b-alpha needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.1 GB (Q2_K) to 7.7 GB (Q8_0).
Starling-LM-7B-alpha – a 7B llama-based LLM fine‑tuned with RLHF and RLAIF
Starling-LM-7B-alpha is a 7‑billion‑parameter language model built on Openchat 3.5 and trained with reinforcement learning from AI feedback. It supports a 8192‑token context window and is released under a CC‑BY‑NC‑4.0 license for non‑commercial use.
Good at
- High‑quality conversational responses
- Strong alignment with GPT‑4‑style judgments
- Efficient inference on modern GPUs
Limits
- No vision or multimodal support
- Requires 8‑k context for full performance
- Non‑commercial license only
Best for
- Chatbot prototypes
- Research demos of RLHF models
- Local inference on mid‑range GPUs
Who it’s for. Developers and researchers who need a well‑aligned 7B llama model for local deployment. The model is suitable for building chat applications and testing RLHF techniques in a non‑commercial setting.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_S | 3.2 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_M | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_L | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_S | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.9 GB | Fits | Get file → | |
| Q5_0 | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_S | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 5.1 GB | 6.7 GB | Fits | Get file → | |
| Q6_K | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q8_0 | 7.7 GB | 9.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K or Q4_K_S (≈5.7 GB memory at 8k context). With 12 GB VRAM, Q5_K_M or Q5_0 (≈6.7 GB). For 16 GB or more, Q6_K (≈7.5 GB) or Q8_0 (≈9.3 GB) gives the best quality. Memory estimates are approximate.
What GPU do you need for berkeley-nest_starling-lm-7b-alpha?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
Which berkeley-nest_starling-lm-7b-alpha quant should you choose?
Q4_K_M is the usual starting point for berkeley-nest_starling-lm-7b-alpha: it balances file size and quality well. Here it is a 4.4 GB file.
The Q8_0 file is 7.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 3.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about berkeley-nest_starling-lm-7b-alpha
How much VRAM does berkeley-nest_starling-lm-7b-alpha need?
About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run berkeley-nest_starling-lm-7b-alpha on an 8 GB GPU?
Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of berkeley-nest_starling-lm-7b-alpha GGUF?
It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.1 GB, Q4_K_S is 4.1 GB and 6 more.
What context length does berkeley-nest_starling-lm-7b-alpha support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download berkeley-nest_starling-lm-7b-alpha GGUF?
The files are on Hugging Face in the TheBloke/Starling-LM-7B-alpha-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does berkeley-nest_starling-lm-7b-alpha use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Starling-LM-7B-alpha on 8 GB VRAM?
Yes, using the Q4_K or Q4_K_S quantization, which requires about 5.7 GB of VRAM at 8k context.
Does the model support image input?
No, Starling-LM-7B-alpha is a text‑only language model with no vision capabilities.
What license applies to the model?
The model is released under a CC‑BY‑NC‑4.0 license, allowing non‑commercial use only.