Xgen 7B 8k Base — Hardware Requirements & GPU Compatibility
Chat
XGen-7B-8K-Base is Salesforce AI Research's 7-billion-parameter pretrained base language model, introduced in the 2023 paper "Long Sequence Modeling with XGen: A 7B LLM Trained on 8K Input Sequence Length" as one of the earlier open 7B models built specifically for longer input sequences. It is not instruction-tuned; a separate XGen-7B-8K-Inst checkpoint, released for research purposes only, adds supervised instruction fine-tuning on top of the same base, and a sibling XGen-7B-4K-Base uses a shorter 4K training sequence length. It uses OpenAI's Tiktoken tokenizer rather than a custom vocabulary. At 7 billion parameters it runs easily on a single consumer GPU. Context length is 8,192 tokens, the model's namesake feature. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in June 2023, predating the wave of 7B open models that followed later that year such as Mistral 7B.
997 downloads
317 likesSpecifications
- Publisher
- Salesforce
- Parameters
- 7B
- Architecture
- LlamaForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 51,200
- Release Date
- 2023-06-28
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Xgen 7B 8k Base Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 3.3 GB | — | 2.98 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 3.8 GB | — | 3.41 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 4.6 GB | — | 4.20 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 5.5 GB | — | 4.99 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 6.3 GB | — | 5.78 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 7.7 GB | — | 7.00 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 15.4 GB | — | 14.00 GB | Brain floating point 16 — preferred for training |
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 Xgen 7B 8k Base?
Q4_K_M · 4.6 GBXgen 7B 8k Base (Q4_K_M) requires 4.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Xgen 7B 8k Base?
Q4_K_M · 4.6 GB59 devices with unified memory can run Xgen 7B 8k Base, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPhone 17.
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightBenchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Xgen 7B 8k Base need?
Xgen 7B 8k Base requires 4.6 GB of VRAM at Q4_K_M, or 15.4 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 7B × 4.8 bits ÷ 8 = 4.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M4.6 GB- What's the best quantization for Xgen 7B 8k Base?
For Xgen 7B 8k Base, Q4_K_M (4.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (5.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.3 GB.
VRAM requirement by quantization
Q2_K3.3 GBQ4_K_M ★4.6 GBQ5_K_M5.5 GBQ6_K6.3 GBQ8_07.7 GBBF1615.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Xgen 7B 8k Base on a Mac?
Xgen 7B 8k Base requires at least 3.3 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 Xgen 7B 8k Base locally?
Yes — Xgen 7B 8k Base can run locally on consumer hardware. At Q4_K_M quantization it needs 4.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Xgen 7B 8k Base?
At Q4_K_M, Xgen 7B 8k Base can reach ~1039 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~142 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 ÷ 4.6 × 0.65 = ~1126 tok/s
Estimated speed at Q4_K_M (4.6 GB)
~1126 tok/s~142 tok/s~1126 tok/s~1039 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Xgen 7B 8k Base?
At Q4_K_M, the download is about 4.20 GB. The full-precision BF16 version is 14.00 GB. The smallest option (Q2_K) is 2.98 GB.
- Which GPUs can run Xgen 7B 8k Base?
52 consumer GPUs can run Xgen 7B 8k Base at Q4_K_M (4.6 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 Xgen 7B 8k Base?
59 devices with unified memory can run Xgen 7B 8k Base at Q4_K_M (4.6 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.