Tower Plus 9B — Hardware Requirements & GPU Compatibility
Chat
Tower Plus 9B is a 9.2B-parameter open language model from Unbabel. It supports a context window of up to 8,192 tokens. At Q4_K_M it needs about 6.46 GB of VRAM — see which GPUs and Macs can run it below.
7.2K downloads
36 likesSpecifications
- Publisher
- Unbabel
- Parameters
- 9.2B
- Architecture
- Gemma2ForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 256,000
- Release Date
- 2025-06-09
- License
- CC BY-NC-SA 4.0
Get Started
HuggingFace
How Much VRAM Does Tower Plus 9B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 4.8 GB | 6.7 GB | 3.93 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 5.4 GB | 7.3 GB | 4.51 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 6.5 GB | 8.3 GB | 5.55 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 7.5 GB | 9.3 GB | 6.58 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 8.5 GB | 10.4 GB | 7.62 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 10.2 GB | 12.0 GB | 9.24 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 19.4 GB | 21.3 GB | 18.48 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 Tower Plus 9B?
Q4_K_M · 6.5 GBTower Plus 9B (Q4_K_M) requires 6.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 9+ GB is recommended. Using the full 8K context window can add up to 1.9 GB, bringing total usage to 8.3 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Tower Plus 9B?
Q4_K_M · 6.5 GB58 devices with unified memory can run Tower Plus 9B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Tower Plus 9B need?
Tower Plus 9B requires 6.5 GB of VRAM at Q4_K_M, or 19.4 GB at BF16. Full 8K context adds up to 1.9 GB (8.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 9.2B × 4.8 bits ÷ 8 = 5.5 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.8 GB (at full 8K context)
VRAM usage by quantization
Q4_K_M6.5 GBQ4_K_M + full context8.3 GB- What's the best quantization for Tower Plus 9B?
For Tower Plus 9B, Q4_K_M (6.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (7.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.8 GB.
VRAM requirement by quantization
Q2_K4.8 GBQ4_K_M ★6.5 GBQ5_K_M7.5 GBQ6_K8.5 GBQ8_010.2 GBBF1619.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Tower Plus 9B on a Mac?
Tower Plus 9B requires at least 4.8 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 Tower Plus 9B locally?
Yes — Tower Plus 9B can run locally on consumer hardware. At Q4_K_M quantization it needs 6.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Tower Plus 9B?
At Q4_K_M, Tower Plus 9B can reach ~681 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~101 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 ÷ 6.5 × 0.65 = ~805 tok/s
Estimated speed at Q4_K_M (6.5 GB)
~805 tok/s~101 tok/s~805 tok/s~681 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Tower Plus 9B?
At Q4_K_M, the download is about 5.55 GB. The full-precision BF16 version is 18.48 GB. The smallest option (Q2_K) is 3.93 GB.
- Which GPUs can run Tower Plus 9B?
50 consumer GPUs can run Tower Plus 9B at Q4_K_M (6.5 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 39 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Tower Plus 9B?
59 devices with unified memory can run Tower Plus 9B at Q4_K_M (6.5 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.