RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run OLMoE 1B 7B 0924 locally?

OLMoE 1B 7B 0924 by allenai has 6.9B parameters (1.3B active per token, 64 experts, 8 used per token). At 4-bit with an 8K context it needs about 5.4 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.

5.4 GBQ4_K_M · 8K context
RTX 4060smallest consumer GPU that fits
M1 16GBsmallest Mac that fits
4Kmax context
MHAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from allenai/OLMoE-1B-7B-0924-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx
2-bit (Q2_K) •rough3.4 GB
3-bit (Q3_K_M) •usable4.1 GB
4-bit (Q4_K_M) •good, most popular4.9 GB
5-bit (Q5_K_M) •very good5.6 GB
6-bit (Q6_K) •near lossless6.3 GB
8-bit (Q8_0) •effectively lossless7.9 GB
16-bit (F16/BF16) •original weights13.9 GB

Which GPUs and Macs run OLMoE 1B 7B 0924?

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 GBFitsQ8_08.4 GB264details
RTX 4060 Ti 16GB16 GBFitsQ8_08.4 GB211details
RTX 309024 GBFitsF1614.4 GB365details
RTX 409024 GBFitsF1614.4 GB393details
RTX 509032 GBFitsF1614.4 GB699details
RTX 5070 Ti16 GBFitsQ8_08.4 GB657details
RX 7900 XTX24 GBFitsF1614.4 GB374details
Mac M4 Pro 48GB48 GBFitsF1614.4 GB106details
Mac M4 Max 128GB128 GBFitsF1614.4 GB213details
Mac M3 Ultra 512GB512 GBFitsF1614.4 GB319details
DGX Spark128 GBFitsF1614.4 GB106details
RTX 407012 GBFitsQ8_08.4 GB370details
RTX 5060 Ti 16GB16 GBFitsQ8_08.4 GB329details
RTX 40608 GBFitsQ6_K6.8 GB258details
Arc B58012 GBFitsQ8_08.4 GB334details
RTX 3060 Ti8 GBFitsQ6_K6.8 GB425details
RTX 30708 GBFitsQ6_K6.8 GB425details
RTX 3080 10GB10 GBFitsQ8_08.4 GB557details
RTX 3080 12GB12 GBFitsQ8_08.4 GB669details
RTX 3090 Ti24 GBFitsF1614.4 GB393details
RTX 4060 Ti 8GB8 GBFitsQ6_K6.8 GB273details
RTX 4070 Super12 GBFitsQ8_08.4 GB370details
RTX 4070 Ti12 GBFitsQ8_08.4 GB370details
RTX 4070 Ti Super16 GBFitsQ8_08.4 GB493details
RTX 408016 GBFitsQ8_08.4 GB526details
RTX 4080 Super16 GBFitsQ8_08.4 GB540details
RTX 50608 GBFitsQ6_K6.8 GB425details
RTX 507012 GBFitsQ8_08.4 GB493details
RTX 508016 GBFitsQ8_08.4 GB704details
2x RTX 30902×24 GBFitsF1614.4 GB365details
2x RTX 40902×24 GBFitsF1614.4 GB393details
2x RTX 50902×32 GBFitsF1614.4 GB699details
RTX A600048 GBFitsF1614.4 GB299details
RTX 6000 Ada48 GBFitsF1614.4 GB374details
RTX PRO 6000 Blackwell96 GBFitsF1614.4 GB699details
L40S48 GBFitsF1614.4 GB337details
A100 40GB40 GBFitsF1614.4 GB606details
A100 80GB80 GBFitsF1614.4 GB795details
H100 PCIe80 GBFitsF1614.4 GB780details
H100 SXM80 GBFitsF1614.4 GB1306details
H200141 GBFitsF1614.4 GB1871details
RX 76008 GBFitsQ6_K6.8 GB273details
RX 7700 XT12 GBFitsQ8_08.4 GB317details
RX 7800 XT16 GBFitsQ8_08.4 GB458details
RX 7900 GRE16 GBFitsQ8_08.4 GB422details
RX 7900 XT20 GBFitsF1614.4 GB312details
RX 907016 GBFitsQ8_08.4 GB469details
RX 9070 XT16 GBFitsQ8_08.4 GB469details
Ryzen AI Max+ 395 128GB128 GBFitsF1614.4 GB100details
Arc A770 16GB16 GBFitsQ8_08.4 GB411details
Mac M1 16GB16 GBFitsQ8_08.4 GB50details
Mac M2 24GB24 GBFitsF1614.4 GB39details
Mac M3 24GB24 GBFitsF1614.4 GB39details
Mac M4 16GB16 GBFitsQ8_08.4 GB88details
Mac M4 32GB32 GBFitsF1614.4 GB47details
Mac M1 Pro 32GB32 GBFitsF1614.4 GB78details
Mac M3 Pro 36GB36 GBFitsF1614.4 GB58details
Mac M4 Pro 24GB24 GBFitsF1614.4 GB106details
Mac M4 Pro 64GB64 GBFitsF1614.4 GB106details
Mac M1 Max 64GB64 GBFitsF1614.4 GB156details
Mac M2 Max 96GB96 GBFitsF1614.4 GB156details
Mac M3 Max 128GB128 GBFitsF1614.4 GB156details
Mac M4 Max 64GB64 GBFitsF1614.4 GB213details
Mac M2 Ultra 192GB192 GBFitsF1614.4 GB312details
Mac M3 Ultra 256GB256 GBFitsF1614.4 GB319details

Questions

How much VRAM does OLMoE 1B 7B 0924 need?

About 5.4 GB at 4-bit (Q4_K_M) with an 8K context: 3.9 GB of weights (real GGUF file size), 1.0 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 8.4 GB.

What is the smallest GPU that runs OLMoE 1B 7B 0924?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).

Can I run OLMoE 1B 7B 0924 on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB or larger, using the default macOS GPU memory limit.

Similar models

Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.

Olmo 3 7B Instruct

7.3B · 7.3 GB at 4-bit

Olmo 3 1025 7B

7.3B · 7.3 GB at 4-bit

Olmo 3 7B Think

7.3B · 7.3 GB at 4-bit

deepseek coder 7b instruct v1.5

6.9B · 8.3 GB at 4-bit

granite 4.0 h tiny

6.9B · 4.6 GB at 4-bit

deepseek coder 6.7b instruct

6.7B · 8.3 GB at 4-bit

Model facts

Hugging Face repoallenai/OLMoE-1B-7B-0924
Parameters6,919,161,856 (6.9B) · ~1.3B active (computed from config)
Layers / hidden size16 / 2048
AttentionMHA; 16 heads, 16 KV heads, head dim 128
KV cache per token (FP16)128.0 KiB
Max context4,096 tokens
Licenseapache-2.0
Released on HFJul 20, 2024
Downloads (30d) / likes45,308 / 159

Sources: Hugging Face model API · config.json (allenai/OLMoE-1B-7B-0924) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.