Vicuna 33B V1.3 — Hardware Requirements & GPU Compatibility
Chat
Vicuna-33B-v1.3 is LMSYS's chat assistant, fine-tuned from Meta's original LLaMA (33B) with supervised instruction tuning on around 125,000 user-shared conversations collected from ShareGPT.com. It was one of the models that popularized using GPT-4 and human preference judging as an evaluation method for open chat models, and is intended primarily for research on large language models and chatbots rather than production deployment. At 33 billion dense parameters it needs a high-end consumer GPU or multi-GPU setup once quantized. Context length is 2,048 tokens, inherited from the original LLaMA base. It is released under a non-commercial license, reflecting both LLaMA's original research-only terms and ShareGPT's usage terms, so it cannot be used commercially. It was published in June 2023; it is an early, now historical Vicuna release, later superseded by Vicuna v1.5 built on Llama 2.
608 downloads
295 likesSpecifications
- Publisher
- LMSYS
- Family
- Vicuna
- Parameters
- 33B
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2023-06-21
Get Started
HuggingFace
How Much VRAM Does Vicuna 33B V1.3 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 15.4 GB | — | 14.03 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 17.7 GB | — | 16.09 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 21.8 GB | — | 19.80 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 25.9 GB | — | 23.51 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 29.9 GB | — | 27.23 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 36.3 GB | — | 33.00 GB | 8-bit quantization, near-lossless |
| FP16est. | 16.00 | 72.6 GB | — | 66.00 GB | Full half-precision — baseline for inference |
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 Vicuna 33B V1.3?
Q4_K_M · 21.8 GBVicuna 33B V1.3 (Q4_K_M) requires 21.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 29+ GB is recommended. 7 GPUs can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Which Devices Can Run Vicuna 33B V1.3?
Q4_K_M · 21.8 GB41 devices with unified memory can run Vicuna 33B V1.3, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightBenchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Vicuna 33B V1.3 need?
Vicuna 33B V1.3 requires 21.8 GB of VRAM at Q4_K_M, or 72.6 GB at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 33B × 4.8 bits ÷ 8 = 19.8 GB
KV Cache + Overhead ≈ 2 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M21.8 GB- Can NVIDIA GeForce RTX 4090 run Vicuna 33B V1.3?
Yes, at Q4_K_M (21.8 GB) or lower. Higher quantizations like Q5_K_M (25.9 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Vicuna 33B V1.3?
For Vicuna 33B V1.3, Q4_K_M (21.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (25.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 15.4 GB.
VRAM requirement by quantization
Q2_K15.4 GBQ4_K_M ★21.8 GBQ5_K_M25.9 GBQ6_K29.9 GBQ8_036.3 GBFP1672.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Vicuna 33B V1.3 on a Mac?
Vicuna 33B V1.3 requires at least 15.4 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 Vicuna 33B V1.3 locally?
Yes — Vicuna 33B V1.3 can run locally on consumer hardware. At Q4_K_M quantization it needs 21.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Vicuna 33B V1.3?
At Q4_K_M, Vicuna 33B V1.3 can reach ~220 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~30 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 ÷ 21.8 × 0.65 = ~239 tok/s
Estimated speed at Q4_K_M (21.8 GB)
~239 tok/s~30 tok/s~239 tok/s~220 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Vicuna 33B V1.3?
At Q4_K_M, the download is about 19.80 GB. The full-precision FP16 version is 66.00 GB. The smallest option (Q2_K) is 14.03 GB.
- Which GPUs can run Vicuna 33B V1.3?
7 consumer GPUs can run Vicuna 33B V1.3 at Q4_K_M (21.8 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run Vicuna 33B V1.3?
41 devices with unified memory can run Vicuna 33B V1.3 at Q4_K_M (21.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.