Vicuna 13B V1.3 — Hardware Requirements & GPU Compatibility
Chat
Vicuna-13B v1.3 is LMSYS's 13-billion-parameter chat assistant, fine-tuned from the original LLaMA base model on roughly 125,000 user-shared conversations collected from ShareGPT via supervised instruction fine-tuning. It was one of the earliest widely used open chat models and helped popularize LLM-as-a-judge and human-preference evaluation methodology, being assessed with standard benchmarks, human preference, and the Chatbot Arena leaderboard. LMSYS positions it as a research and hobbyist tool rather than a production assistant. At 13B parameters it needs a capable consumer GPU at full precision, considerably less once quantized. Context length is 2,048 tokens, inherited from the original LLaMA base model. It carries a non-commercial license, consistent with LLaMA's original research-only weights. It was published in June 2023.
Runs great on a 24 GB GPU
Runs from 8 GB (Q3_K_M · 2K)Best on 24 GB (Q4_K_M · ~76 tok/s · 2K)Macs from 16 GB (Q4_K_M · ~16 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Vicuna 13B V1.3
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve lmsys/vicuna-13b-v1.3 --max-model-len 2048vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (3 GB headroom) · Q4_K_M
- Generation speed
- ~69 tok/s
- generation speed
- Cost per 1M output tokens
- $0.49
- per 1M output tokens
How Much VRAM Does Vicuna 13B V1.3 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 6.1 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 2K context · ~108 tok/s | |
| 7.0 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 2K context · ~94 tok/s | |
| 8.6 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 2K context · ~76 tok/s | |
| 10.2 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~64 tok/s | |
| 11.8 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 2K context · ~56 tok/s | |
| 14.3 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 2K context · ~46 tok/s | |
| 28.6 GB | — | 16-bit · full — Full half-precision — baseline for inference | Does not fit: needs 28.6 GB |
Selected Q4_K_M
4-bit medium quantization8.6GBat 2K context
- Weights
- 7.9 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 15.4 GB free · ~76 tok/s
≥50 tok/s needs ≥659 GB/s · RTX 5090 ~136, RTX 3090 Ti ~76
Which Hardware Can Run Vicuna 13B V1.3?
Q4_K_M · 8.6 GBVicuna 13B V1.3 (Q4_K_M) requires 8.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 12+ GB is recommended. 40 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti. 150 devices with unified memory can run Vicuna 13B V1.3, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M2 Pro (16 GB).
12 GB
12 GB tier →fits · 3.4 GB free · up to 2K ctx
10 GPUs
RTX 3080 Ti~69Simulate output on RTX 3080 TiRTX 5070~51Simulate output on RTX 5070RTX 4070~38Simulate output on RTX 407020 GB
fits · 11.4 GB free · up to 2K ctx
1 GPU
RX 7900 XT~56Simulate output on RX 7900 XT32–40 GB
fits · 23.4 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~136Simulate output on RTX 5090M5 Max36 GB~38Simulate output on Mac Studio M5 Max (36 GB)M532 GB~13Simulate output on MacBook Air 13" M5 (32 GB)Orin~16Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~10Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Vicuna 13B V1.3?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 2 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
Alternatives to Vicuna 13B V1.3
Vicuna family · 3 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Gemma 3 12B ITGoogle | 74.2 | 10.9 GB | ~82 | same size |
| Mistral Nemo Base 2407Mistral AI | — | 11 GB | ~81 | same size |
| Phi 3 Medium 128k InstructMicrosoft | — | 12 GB | ~72 | same size |
| Baichuan2 13B Basebaichuan-inc | — | 11.5 GB | ~76 | same size |
| Llama 2 13B Chat HFMeta | — | 11.5 GB | ~76 | same size |
| Vllm Translategemma 12B ITchbae624 | — | 9.8 GB | ~73 | same size |
Specifications
- Publisher
- LMSYS
- Family
- Vicuna
- Parameters
- 13B
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2023-06-18
Frequently Asked Questions
How much VRAM does Vicuna 13B V1.3 need?
Vicuna 13B V1.3 requires 8.6 GB of VRAM at Q4_K_M, or 28.6 GB at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 13B × 4.8 bits ÷ 8 = 7.8 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Vicuna 13B V1.3?
Yes, at Q8_0 (14.3 GB) or lower. Higher quantizations like FP16 (28.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Vicuna 13B V1.3?
For Vicuna 13B V1.3, Q4_K_M (8.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (10.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 6.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Vicuna 13B V1.3 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Vicuna 13B V1.3. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 8.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Vicuna 13B V1.3 locally?
Yes — Vicuna 13B V1.3 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Vicuna 13B V1.3?
At Q4_K_M, Vicuna 13B V1.3 can reach ~559 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~76 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 ÷ 8.58 × 0.65 = ~606 tok/s
Estimated speed at Q4_K_M (8.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Vicuna 13B V1.3?
At Q4_K_M, the download is about 7.80 GB. The full-precision FP16 version is 26.00 GB. The smallest option (Q2_K) is 5.53 GB.
Which GPUs can run Vicuna 13B V1.3?
40 consumer GPUs can run Vicuna 13B V1.3 at Q4_K_M. Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
Which devices can run Vicuna 13B V1.3?
150 devices with unified memory can run Vicuna 13B V1.3 at Q4_K_M (8.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.