Yi 34B — Hardware Requirements & GPU Compatibility
Chat
Yi-34B is 01.AI's base pretrained language model, not instruction-tuned, with about 34.4 billion dense parameters trained on a 3-trillion-token bilingual Chinese-English corpus. At release it ranked first among open-source base models on benchmarks including the Hugging Face Open LLM Leaderboard and C-Eval, ahead of larger models such as Falcon-180B and Llama-2-70B. A long-context Yi-34B-200K variant and an instruction-tuned Yi-34B-Chat were released alongside it. Running the dense 34B model requires a high-end consumer GPU or multi-GPU setup, especially unquantized. Context length is 4,096 tokens, the default window for the 34B series before the extended 200K variant. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. It was published in November 2023; by current standards it is an older-generation base model, since superseded by 01.AI's Yi-1.5 and later families.
Decent on a 24 GB GPU
Runs from 12 GB (IQ2_XS · 4K)Best on 24 GB (Q4_K_M · ~31 tok/s · 4K)Macs from 16 GB (IQ2_S · ~12 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Yi 34B
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
ollama run hf.co/mradermacher/Yi-34B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 2.1 GB free · 4K context
Download: Yi-34B.Q4_K_M.gguf20.66 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 5090 (32 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~54 tok/s
- generation speed
- Cost per 1M output tokens
- $2.54
- per 1M output tokens
How Much VRAM Does Yi 34B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.4 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 4K context · ~43 tok/s | |
| 15.8 GB | — | 3-bit small — 3-bit small quantization | Fits: 4K context · ~41 tok/s | |
| 17.6 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 4K context · ~37 tok/s | |
| 18 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 4K context · ~36 tok/s | |
| 21.4 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 4K context · ~31 tok/s | |
| 25.3 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 25.3 GB | |
| 29.2 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 29.2 GB | |
| 35.2 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 35.2 GB |
Selected Q4_K_M
4-bit medium quantization21.9GBat 4K context
- Weights
- 20.6 GB
- KV cache
- 1.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 2.1 GB free · ~31 tok/s
≥50 tok/s needs ≥1.65 TB/s · RTX 5090 ~54
Or .
Which Hardware 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. 7 GPUs can run it, including NVIDIA GeForce RTX 5090. 100 devices with unified memory can run Yi 34B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit IQ4_XS (19.8 GB)
1 GPU
RX 7900 XT~25Simulate output on RX 7900 XT32–40 GB
fits · 10.1 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~54Simulate output on RTX 5090M5 Max36 GB~15Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~6Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Yi 34B?
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 4 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- MMLU-Pro
TIGER-LabIndependent
Independent43.0%
#94/146 open
- MMLU
Epoch AI · Nov 2023Lab-reported
Lab-reported76.3%
#18/85 open
- BIG-Bench Hard
Epoch AI · Nov 2023Lab-reported
Lab-reported54.3%
#17/38 open
- GSM8K
Epoch AI · Nov 2023Lab-reported
Lab-reported67.2%
#20/62 open
Alternatives to Yi 34B
Yi family · 6 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Nanbeige4.3 33BNanbeige | — | 23.7 GB | ~32 | same size |
| Sage A1.5InternScience | — | 22 GB | ~151 | same size |
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
Specifications
- Publisher
- 01.AI
- Family
- Yi
- Parameters
- 34.4B
- Architecture
- LlamaForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 64,000
- Release Date
- 2023-11-01
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Yi 34B need?
Yi 34B requires 21.4 GB of VRAM at Q4_K_M, or 69.6 GB at BF16.
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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 1.3 GB (at full 4K context)
VRAM usage by quantization
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 IQ2_XXS at 10.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Yi 34B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Yi 34B, the smallest at IQ2_S. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 21.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run Yi 34B locally?
Yes — Yi 34B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Yi 34B?
At Q4_K_M, Yi 34B can reach ~224 tok/s on AMD Instinct MI350X. 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: NVIDIA B200 → 8000 ÷ 21.4 × 0.65 = ~243 tok/s
Estimated speed at Q4_K_M (21.4 GB)
Real-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 BF16 version is 68.78 GB. The smallest option (IQ2_XXS) is 9.46 GB.
Which GPUs can run Yi 34B?
7 consumer GPUs can run Yi 34B at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
Which devices can run Yi 34B?
100 devices with unified memory can run Yi 34B at Q4_K_M (21.4 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.