Yi 34B — Hardware Requirements & GPU Compatibility
Chat
Yi 34B is a 34.4B-parameter open language model from 01.AI in the Yi family. It supports a context window of up to 4,096 tokens. At Q4_K_M it needs about 21.44 GB of VRAM — see which GPUs and Macs can run it below.
10.2K downloads
1.3K likesSpecifications
- Publisher
- 01.AI
- Family
- Yi
- Parameters
- 34.4B
- Architecture
- LlamaForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 64,000
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Yi 34B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 15.4 GB | 15.9 GB | 14.62 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 15.8 GB | 16.4 GB | 15.05 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 17.6 GB | 18.1 GB | 16.76 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 18 GB | 18.5 GB | 17.19 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 21.4 GB | 21.9 GB | 20.63 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 25.3 GB | 25.8 GB | 24.50 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 29.2 GB | 29.7 GB | 28.37 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 35.2 GB | 35.7 GB | 34.39 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Yi 34B?
Q4_K_M · 21.4 GBYi 34B (Q4_K_M) requires 21.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. Using the full 4K context window can add up to 0.5 GB, bringing total usage to 21.9 GB. 5 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 Yi 34B?
Q4_K_M · 21.4 GB21 devices with unified memory can run Yi 34B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightBenchmarks
View all 3 →Related Models
Derivatives (2)
Frequently Asked Questions
- How much VRAM does Yi 34B need?
Yi 34B requires 21.4 GB of VRAM at Q4_K_M, or 35.2 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 34.4B × 4.8 bits ÷ 8 = 20.6 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.3 GB (at full 4K context)
VRAM usage by quantization
Q4_K_M21.4 GBQ4_K_M + full context21.9 GB- Can NVIDIA GeForce RTX 4090 run Yi 34B?
Yes, at Q5_0 (22.3 GB) or lower. Higher quantizations like Q5_K_S (24.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Yi 34B?
For Yi 34B, Q4_K_M (21.4 GB) offers the best balance of quality and VRAM usage. Q5_0 (22.3 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 15.0 GB.
VRAM requirement by quantization
IQ3_XS15.0 GBIQ3_M16.3 GBIQ4_XS19.3 GBQ4_K_M ★21.4 GBQ5_022.3 GBQ8_035.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Yi 34B on a Mac?
Yi 34B requires at least 15.0 GB at IQ3_XS, 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 Yi 34B locally?
Yes — Yi 34B can run locally on consumer hardware. At Q4_K_M quantization it needs 21.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Yi 34B?
At Q4_K_M, Yi 34B can reach ~136 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~31 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 21.4 × 0.55 = ~136 tok/s
Estimated speed at Q4_K_M (21.4 GB)
~136 tok/s~31 tok/s~102 tok/s~84 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Yi 34B?
At Q4_K_M, the download is about 20.63 GB. The full-precision Q8_0 version is 34.39 GB. The smallest option (IQ3_XS) is 14.19 GB.
- Which GPUs can run Yi 34B?
5 consumer GPUs can run Yi 34B at Q4_K_M (21.4 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run Yi 34B?
21 devices with unified memory can run Yi 34B at Q4_K_M (21.4 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.