Yi 1.5 34B Chat
By 01.AI · China
Updated 2026-07-13
Overview
01.AI's dense 34B chat model under Apache 2.0, trained on 3.6T tokens with strong English-Chinese bilingual quality.
When to pick this model
- Chinese-English bilingual chat needing open weights
- Llama-compatible tooling pipelines at the 34B scale
- Research baselines from the 2024 dense-34B era
- Workloads where Apache 2.0 is mandatory at 34B
- Use cases where Qwen 2.5 32B isn't an option
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 20 GB |
| Q5_K_M | 24 GB |
| Q8_0 | 36 GB |
| FP16 (no quantization) | 68 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Yi 1.5 34B Chat wants a 24 GB card at Q4_K_M (20 GB). Stepping up to Q8_0 nearly doubles the footprint to 36 GB, and unquantized FP16 weights take 68 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Yi 1.5 34B Chat needs roughly 32 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 3 tokens/sec on entry-level GPUs, on the order of 12 tokens/sec on a mid-range card, and up to 30 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Yi 1.5 34B Chat to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Yi 1.5 34B Chat |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 20 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 20 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Does not fit — needs 20 GB at Q4_K_M |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Q5_K_M (24 GB used) |
| 32 GB | RTX 5090 | Q5_K_M (24 GB used) |
Which GPU should you buy to run Yi 1.5 34B Chat?
To run Yi 1.5 34B Chat locally at Q4, you need ~20 GB of VRAM. The best value for this is a RTX 4090 (24 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Published benchmark scores
| Benchmark | Score |
|---|---|
| MMLU | 77.2 |
| HumanEval | 75.2 |
Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.
To put Yi 1.5 34B Chat in context: its MMLU score of 77.2 ranks #13 of the 34 catalog models with a published MMLU result (catalog median 73.4); its HumanEval score of 75.2 ranks #16 of the 26 catalog models with a published HumanEval result (catalog median 81.1). Scores are author-published and measured under different harnesses, so treat gaps of a few points as noise rather than a verdict.
Strengths
- Excellent Chinese-language performance
- Compatible with Llama tooling and quantization
- Apache 2.0 license enables free commercial use
- Stable chat behavior and well-understood quirks
Limitations
- 4096-token context is severely limiting today
- Outclassed by Qwen 2.5 32B in 2025
- No multimodal or tool-use specialization
Typical workloads
In our catalog grid, Yi 1.5 34B Chat is filed under Alternative Chat, CN/EN Multilingual — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multilingual workloads.
Note the 4k-token context window — fine for short interactions, limiting for long documents or big retrieval contexts. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.
Architecture & training
Architecture: Dense Transformer · 34B · Yi 1.5 · Llama-compatible
Training: 01.AI — 3.1T multilingual EN/ZH tokens. Successor to Yi-34B.
A competent Apache-licensed bilingual 34B from 2024 — only pick it over Qwen 2.5 32B when license terms force your hand.
Quick start
ollama run yi:34bOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Yi 1.5 34B Chat need?
At the recommended Q4_K_M quantization, Yi 1.5 34B Chat needs about 20 GB of VRAM. Q8_0 takes 36 GB, and unquantized FP16 weights take 68 GB.
Can Yi 1.5 34B Chat run without a GPU?
Yes — with roughly 32 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Yi 1.5 34B Chat support?
Yi 1.5 34B Chat supports a 4k-token context window (4,096 tokens).
Can I use Yi 1.5 34B Chat commercially?
Yes. Yi 1.5 34B Chat is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Yi 1.5 34B Chat on consumer hardware?
Our compatibility engine estimates on the order of 12 tokens/sec on a mid-range GPU and up to 30 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Yi 1.5 34B Chat should I download first?
Start with Q4_K_M (20 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q5_K_M.