Yi 1.5 34B Chat — Hardware Requirements & GPU Compatibility
Chat
Yi 1.5 34B Chat is a 34.4-billion parameter instruction-tuned model by 01.AI, the Chinese AI lab founded by Kai-Fu Lee. It is a bilingual model with strong performance in both English and Chinese, making it particularly well suited for users who need high-quality generation in either language. Yi 1.5 represents an improved iteration of the Yi model family with enhanced reasoning and coding ability. The 34B size requires a GPU with at least 24GB of VRAM for quantized inference, placing it within reach of high-end consumer cards like the RTX 4090. Released under the Yi License.
12.2K downloads
274 likesSpecifications
- Publisher
- 01.AI
- Family
- Yi 1.5
- 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 1.5 34B Chat Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| IQ2_M | 2.70 | 12.4 GB | 12.9 GB | 11.61 GB | Importance-weighted 2-bit, medium |
| IQ3_XS | 3.30 | 15.0 GB | 15.5 GB | 14.19 GB | Importance-weighted 3-bit, extra small |
| IQ3_S | 3.40 | 15.4 GB | 15.9 GB | 14.62 GB | Importance-weighted 3-bit, small |
| 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 |
| IQ3_M | 3.60 | 16.3 GB | 16.8 GB | 15.48 GB | Importance-weighted 3-bit, medium |
| 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 |
| Q3_K_L | 4.10 | 18.4 GB | 18.9 GB | 17.62 GB | 3-bit large quantization |
| IQ4_XS | 4.30 | 19.3 GB | 19.8 GB | 18.48 GB | Importance-weighted 4-bit, compact |
| IQ4_NL | 4.50 | 20.1 GB | 20.6 GB | 19.34 GB | Importance-weighted 4-bit, non-linear |
| Q4_K_S | 4.50 | 20.1 GB | 20.6 GB | 19.34 GB | 4-bit small quantization |
| Q4_K_M | 4.80 | 21.4 GB | 21.9 GB | 20.63 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_0 | 5.00 | 22.3 GB | 22.8 GB | 21.49 GB | 5-bit legacy quantization |
| Q5_K_S | 5.50 | 24.4 GB | 24.9 GB | 23.64 GB | 5-bit small quantization |
| 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 1.5 34B Chat?
Q4_K_M · 21.4 GBYi 1.5 34B Chat (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 1.5 34B Chat?
Q4_K_M · 21.4 GB21 devices with unified memory can run Yi 1.5 34B Chat, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Derivatives (5)
Similar
Frequently Asked Questions
- How much VRAM does Yi 1.5 34B Chat need?
Yi 1.5 34B Chat 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 1.5 34B Chat?
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 1.5 34B Chat?
For Yi 1.5 34B Chat, 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 IQ2_M at 12.4 GB.
VRAM requirement by quantization
IQ2_M12.4 GB~62%Q3_K_S15.8 GB~77%IQ4_XS19.3 GB~87%Q4_K_M ★21.4 GB~89%Q5_022.3 GB~90%Q8_035.2 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run Yi 1.5 34B Chat on a Mac?
Yi 1.5 34B Chat requires at least 12.4 GB at IQ2_M, 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 1.5 34B Chat locally?
Yes — Yi 1.5 34B Chat 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 1.5 34B Chat?
At Q4_K_M, Yi 1.5 34B Chat 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)
AMD Instinct MI300X~136 tok/sNVIDIA GeForce RTX 4090~31 tok/sNVIDIA H100 SXM~102 tok/sAMD Instinct MI250X~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 1.5 34B Chat?
At Q4_K_M, the download is about 20.63 GB. The full-precision Q8_0 version is 34.39 GB. The smallest option (IQ2_M) is 11.61 GB.