Starling LM 7B Beta — Hardware Requirements & GPU Compatibility
Chat
Starling-LM-7B-beta is Nexusflow's chat model, fine-tuned from Openchat-3.5-0106 (itself based on Mistral-7B-v0.1) using reinforcement learning from AI feedback (RLAIF). It was trained with Nexusflow's own 34B reward model and a PPO-based policy optimization pipeline on the Nectar preference dataset, and scored 8.12 on MT-Bench with GPT-4 as judge, an improvement over the team's earlier Starling model. It uses OpenChat's exact chat template rather than a generic one. At 7 billion parameters it runs comfortably on a single consumer GPU. Context length is 8,192 tokens. It is released under the Apache 2.0 license with an added condition that it not be used to compete with OpenAI, reflecting that its Nectar training data was generated with GPT-4. It was published in March 2024.
1.6K downloads
343 likesSpecifications
- Publisher
- Nexusflow
- Parameters
- 7.2B
- Architecture
- MistralForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 32,002
- Release Date
- 2024-03-19
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Starling LM 7B Beta Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 3.6 GB | 4.5 GB | 3.08 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 3.7 GB | 4.5 GB | 3.17 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 4.1 GB | 4.9 GB | 3.53 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 4.2 GB | 5.0 GB | 3.62 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 4.9 GB | 5.7 GB | 4.35 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 5.7 GB | 6.5 GB | 5.16 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 6.5 GB | 7.3 GB | 5.97 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 7.8 GB | 8.6 GB | 7.24 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Starling LM 7B Beta?
Q4_K_M · 4.9 GBStarling LM 7B Beta (Q4_K_M) requires 4.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 8K context window can add up to 0.8 GB, bringing total usage to 5.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Starling LM 7B Beta?
Q4_K_M · 4.9 GB59 devices with unified memory can run Starling LM 7B Beta, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Apple iPhone 17 Pro.
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download Starling LM 7B Beta
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Starling LM 7B Beta need?
Starling LM 7B Beta requires 4.9 GB of VRAM at Q4_K_M, or 15.1 GB at BF16. Full 8K context adds up to 0.8 GB (5.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 7.2B × 4.8 bits ÷ 8 = 4.3 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.4 GB (at full 8K context)
VRAM usage by quantization
Q4_K_M4.9 GBQ4_K_M + full context5.7 GB- What's the best quantization for Starling LM 7B Beta?
For Starling LM 7B Beta, Q4_K_M (4.9 GB) offers the best balance of quality and VRAM usage. Q5_0 (5.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.6 GB.
VRAM requirement by quantization
Q2_K3.6 GBQ4_04.2 GBQ4_K_M ★4.9 GBQ5_05.1 GBQ5_K_M5.7 GBBF1615.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Starling LM 7B Beta on a Mac?
Starling LM 7B Beta requires at least 3.6 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Starling LM 7B Beta locally?
Yes — Starling LM 7B Beta can run locally on consumer hardware. At Q4_K_M quantization it needs 4.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Starling LM 7B Beta?
At Q4_K_M, Starling LM 7B Beta can reach ~978 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~133 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 4.9 × 0.65 = ~1059 tok/s
Estimated speed at Q4_K_M (4.9 GB)
~1059 tok/s~133 tok/s~1059 tok/s~978 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Starling LM 7B Beta?
At Q4_K_M, the download is about 4.35 GB. The full-precision BF16 version is 14.48 GB. The smallest option (Q2_K) is 3.08 GB.
- Which GPUs can run Starling LM 7B Beta?
52 consumer GPUs can run Starling LM 7B Beta at Q4_K_M (4.9 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Starling LM 7B Beta?
59 devices with unified memory can run Starling LM 7B Beta at Q4_K_M (4.9 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.