RunsOnMy ModelsGPUs & MacsAPI pricesVRAM calculatorNew

Can I run Yi 34B Chat locally?

Yi 34B Chat by 01-ai has 34B parameters. At 4-bit with an 8K context it needs about 21.6 GB of GPU memory. It fits on 36 of 65 GPUs and Macs we track.

21.6 GBQ4_K_M · 8K context
RTX 5090smallest consumer GPU that fits
M3 Pro 36GBsmallest Mac that fits
4Kmax context
GQAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from TheBloke/Yi-34B-Chat-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx
2-bit (Q2_K) •rough15.0 GB
3-bit (Q3_K_M) •usable17.0 GB
4-bit (Q4_K_M) •good, most popular20.7 GB
5-bit (Q5_K_M) •very good24.1 GB
6-bit (Q6_K) •near lossless27.7 GB
8-bit (Q8_0) •effectively lossless35.5 GB
16-bit (F16/BF16)original weights65.5 GB

Which GPUs and Macs run Yi 34B Chat?

Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)
RTX 3060 12GB12 GBNo———details
RTX 4060 Ti 16GB16 GBNo———details
RTX 309024 GBFitsQ3_K_M17.9 GB56details
RTX 409024 GBFitsQ3_K_M17.9 GB61details
RTX 509032 GBFitsQ5_K_M25.0 GB74details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBFitsQ3_K_M17.9 GB58details
Mac M4 Pro 48GB48 GBFitsQ6_K28.7 GB9.7details
Mac M4 Max 128GB128 GBFitsF1666.5 GB7.9details
Mac M3 Ultra 512GB512 GBFitsF1666.5 GB12details
DGX Spark128 GBFitsF1666.5 GB4.0details
RTX 407012 GBNo———details
RTX 5060 Ti 16GB16 GBNo———details
RTX 40608 GBNo———details
Arc B58012 GBNo———details
RTX 3060 Ti8 GBNo———details
RTX 30708 GBNo———details
RTX 3080 10GB10 GBNo———details
RTX 3080 12GB12 GBNo———details
RTX 3090 Ti24 GBFitsQ3_K_M17.9 GB61details
RTX 4060 Ti 8GB8 GBNo———details
RTX 4070 Super12 GBNo———details
RTX 4070 Ti12 GBNo———details
RTX 4070 Ti Super16 GBNo———details
RTX 408016 GBNo———details
RTX 4080 Super16 GBNo———details
RTX 50608 GBNo———details
RTX 507012 GBNo———details
RTX 508016 GBNo———details
2x RTX 30902×24 GBFitsQ8_036.4 GB26details
2x RTX 40902×24 GBFitsQ8_036.4 GB28details
2x RTX 50902×32 GBFitsQ8_036.4 GB49details
RTX A600048 GBFitsQ8_036.4 GB21details
RTX 6000 Ada48 GBFitsQ8_036.4 GB26details
RTX PRO 6000 Blackwell96 GBFitsF1666.5 GB26details
L40S48 GBFitsQ8_036.4 GB24details
A100 40GB40 GBFitsQ6_K28.7 GB55details
A100 80GB80 GBFitsF1666.5 GB30details
H100 PCIe80 GBFitsF1666.5 GB29details
H100 SXM80 GBFitsF1666.5 GB49details
H200141 GBFitsF1666.5 GB70details
RX 76008 GBNo———details
RX 7700 XT12 GBNo———details
RX 7800 XT16 GBNo———details
RX 7900 GRE16 GBNo———details
RX 7900 XT20 GBFitsQ2_K16.0 GB55details
RX 907016 GBNo———details
RX 9070 XT16 GBNo———details
Ryzen AI Max+ 395 128GB128 GBFitsF1666.5 GB3.7details
Arc A770 16GB16 GBNo———details
Mac M1 16GB16 GBNo———details
Mac M2 24GB24 GBTightQ2_K16.0 GB6.9details
Mac M3 24GB24 GBTightQ2_K16.0 GB6.9details
Mac M4 16GB16 GBNo———details
Mac M4 32GB32 GBFitsQ3_K_M17.9 GB7.2details
Mac M1 Pro 32GB32 GBFitsQ3_K_M17.9 GB12details
Mac M3 Pro 36GB36 GBFitsQ4_K_M21.6 GB7.3details
Mac M4 Pro 24GB24 GBTightQ2_K16.0 GB19details
Mac M4 Pro 64GB64 GBFitsQ8_036.4 GB7.5details
Mac M1 Max 64GB64 GBFitsQ8_036.4 GB11details
Mac M2 Max 96GB96 GBFitsQ8_036.4 GB11details
Mac M3 Max 128GB128 GBFitsF1666.5 GB5.8details
Mac M4 Max 64GB64 GBFitsQ8_036.4 GB15details
Mac M2 Ultra 192GB192 GBFitsF1666.5 GB12details
Mac M3 Ultra 256GB256 GBFitsF1666.5 GB12details

Questions

How much VRAM does Yi 34B Chat need?

About 21.6 GB at 4-bit (Q4_K_M) with an 8K context: 19.2 GB of weights (real GGUF file size), 1.9 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 36.4 GB.

What is the smallest GPU that runs Yi 34B Chat?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 5090 (32 GB).

Can I run Yi 34B Chat on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M3 Pro 36GB or larger, using the default macOS GPU memory limit.

Model facts

Hugging Face repo01-ai/Yi-34B-Chat
Parameters34,388,917,248 (34B)
Layers / hidden size60 / 7168
AttentionGQA; 56 heads, 8 KV heads, head dim 128
KV cache per token (FP16)240.0 KiB
Max context4,096 tokens
Licenseapache-2.0
Released on HFNov 22, 2023
Downloads (30d) / likes29,743 / 358

Sources: Hugging Face model API · config.json (01-ai/Yi-34B-Chat) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.