Skip to content

Qwen3 14B VRAM Requirements

Alibaba, China · Released April 27, 2025

Qwen3 14B has 14.8B parameters. In BF16 its weights alone take 27.5 GiB; quantized to 4-bit, about 8.46 GiB. Each 32K-token request adds 5.00 GiB of KV cache. Cheapest way to run it today: 1 × GeForce RTX 3090 (24 GB) at $0.143 per hour.

Size your own setup in the calculator →

VRAM by precision and context length

Weights plus the KV cache of one request (BF16 cache), in GiB. Add 1 to 3 GiB for the inference engine itself.

Weights formatWeights only+ 8K context+ 32K context
BF16 / FP1627.528.832.5
FP8 / INT815.216.520.2
4-bit (GGUF Q4_K_M)8.469.7113.5

Qwen3 14B GGUF files

Exact size of each quantization in unsloth/Qwen3-14B-GGUF (opens in a new tab), and the smallest GPU that runs it with llama.cpp, Ollama or LM Studio and an 8K-token context.

QuantizationFile sizeSmallest GPU
BF1627.5 GiBRTX 5090 (32 GB)
UD-Q8_K_XL17.5 GiBRTX 4090 (24 GB)
Q8_014.6 GiBRTX 4090 (24 GB)
UD-Q6_K_XL12.4 GiBRTX 4080 / 4080 SUPER (16 GB)
Q6_K11.3 GiBRTX 4080 / 4080 SUPER (16 GB)
UD-Q5_K_XL9.82 GiBRTX 4080 / 4080 SUPER (16 GB)
Q5_K_M9.79 GiBRTX 4080 / 4080 SUPER (16 GB)
Q5_K_S9.56 GiBRTX 4070 / 4070 SUPER (12 GB)
Q4_18.74 GiBRTX 4070 / 4070 SUPER (12 GB)
UD-Q4_K_XL8.53 GiBRTX 4070 / 4070 SUPER (12 GB)
Q4_K_M8.38 GiBRTX 4070 / 4070 SUPER (12 GB)
Q4_K_S7.98 GiBRTX 4070 / 4070 SUPER (12 GB)
Q4_07.96 GiBRTX 4070 / 4070 SUPER (12 GB)
IQ4_NL7.95 GiBRTX 4070 / 4070 SUPER (12 GB)
IQ4_XS7.58 GiBRTX 4070 / 4070 SUPER (12 GB)
UD-Q3_K_XL7.07 GiBRTX 4070 / 4070 SUPER (12 GB)
Q3_K_M6.82 GiBRTX 4070 / 4070 SUPER (12 GB)
Q3_K_S6.20 GiBRTX 4070 / 4070 SUPER (12 GB)
UD-Q2_K_XL5.65 GiBRTX 4060 (8 GB)
UD-IQ3_XXS5.60 GiBRTX 4060 (8 GB)
Q2_K_L5.53 GiBRTX 4060 (8 GB)
Q2_K5.36 GiBRTX 4060 (8 GB)
UD-IQ2_M5.05 GiBRTX 4060 (8 GB)
UD-IQ2_XXS4.16 GiBRTX 4060 (8 GB)
UD-IQ1_M3.79 GiBRTX 4060 (8 GB)
UD-IQ1_S3.56 GiBRTX 4060 (8 GB)

Read every day from Hugging Face. Split files are added together; vision projectors are left out.

How many GPUs to run Qwen3 14B

Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.

GPUBF16 / FP168-bit4-bit
GeForce RTX 4090 24 GB211
GeForce RTX 5090 32 GB111
RTX PRO 6000 Blackwell 96 GB111
Mac M5 Max 128 GB 96 GB usable111
NVIDIA H100 80 GB111
NVIDIA H200 141 GB111
NVIDIA B200 (HGX) 180 GB111

8-bit: FP8 with vLLM (INT8 on GPUs without FP8), Q8_0 with llama.cpp. 4-bit: AWQ / GPTQ with vLLM, Q4_K_M with llama.cpp, both counted at the Q4_K_M size.

Cheapest way to run Qwen3 14B today

For each GPU: the fewest cards that fit Qwen3 14B with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-10-11).

On-demand prices from RunPod, Vast.ai, Verda and Azure, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.

KV cache: how memory grows with context

Architecture: 40 layers · 40 full attention (8 KV × 128). Every layer keeps keys and values for every token (grouped-query attention), so the cache grows linearly with context.

Context per requestBF16 cacheFP8 cache
8K tokens1.25 GiB0.63 GiB
32K tokens5.00 GiB2.50 GiB

Qwen3 14B VRAM FAQ

How much VRAM does Qwen3 14B need?

In BF16 the weights alone take 27.5 GiB (30 GB). In FP8 that is 15.2 GiB, and about 8.46 GiB with 4-bit quantization (Q4_K_M). Each request then adds KV cache: 1.25 GiB at 8K tokens and 5.00 GiB at 32K (BF16 cache).

Can Qwen3 14B run on a single RTX 4090 (24 GB)?

Yes. In Q8_0 it fits on one RTX 4090 with an 8K-token context (16.5 GiB including the cache, with llama.cpp).

What is the cheapest way to run Qwen3 14B?

On 2026-10-11, the cheapest on-demand setup is 1 × GeForce RTX 3090 (24 GB) with Q8_0 weights on Vast.ai, at $0.143 per hour (about $104.39 per month). Next: 1 × NVIDIA L4 (24 GB) with FP8 weights on Vast.ai, at $0.268 per hour. Sized for one 8K-token request; prices are checked every hour.

How many H100 GPUs does Qwen3 14B need?

With one request and an 8K-token context: 1 in BF16, 1 in FP8 and 1 in 4-bit (vLLM, 90% of memory usable). Serving many users at once needs more memory for their KV caches: the calculator sizes that for you.

Qwen3 14B VRAM badge

For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/qwen3-14b.json.

Qwen3 14B VRAM badge

[![Qwen3 14B VRAM](https://studiotvai.com/badge/qwen3-14b.svg)](https://studiotvai.com/vram-requirements/qwen3-14b)

Other models

Same family (dense): Llama 3.1 8B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 405B · Youtu-Parsing-Omni · Mistral 7B-v0.3 · Mistral-Small-3.1 24B · Mistral-Nemo · DeepSeek-R1-Qwen3 8B · DeepSeek-R1-Distill-Qwen 32B · DeepSeek-R1-Distill-Qwen 14B · DeepSeek-R1-Distill-Qwen 7B · DeepSeek-R1-Distill-Llama 8B · Qwen3 4B · Qwen3 8B · Qwen2.5 7B · Qwen2.5 3B · Qwen2.5 32B · Qwen2.5 14B

All models: Llama 3.1 8B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 405B · Qwen3.5 4B · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · LFM2.5 8B-A1B · LFM2 24B-A2B · Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Scout 17B-16E · Llama 4 Maverick 17B-128E · Kolibri-1 · Nemotron 3 Nano 30B-A3B · Nemotron 3 Super 120B-A12B · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Kimi K3 · Mistral Large 4 · Qwen3-Coder-Next 80B-A3B · Qwen3-Coder 30B-A3B · Qwen3-Coder 480B-A35B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Atria Dawn Preview · Intern S2 397B · Clef · Clef Flash · D1 3B · Humanizer · JEV 27B VL · Mellum2.1 12B-A2.5B · LightOnOCR-3 4B · Spark-X2.5 4B · Agnes-3.0-Qwen · Youtu-Parsing-Omni · Agnes-3.0-Flash · Mistral 7B-v0.3 · Mistral-Small-3.1 24B · Mistral-Nemo · Ministral 8B · DeepSeek-V3 · DeepSeek-R1-Qwen3 8B · DeepSeek-R1-Distill-Qwen 32B · DeepSeek-V3.1 · DeepSeek-R1-Distill-Qwen 14B · DeepSeek-R1-Distill-Qwen 7B · DeepSeek-R1-Distill-Llama 8B · Qwen3 4B · Qwen3 8B · Qwen2.5 7B · Qwen2.5 3B · Qwen3.6 27B · Qwen3.5 27B · Qwen2.5-Coder 7B · Qwen2.5 32B · Qwen2.5-Coder 14B · Qwen3.5 35B-A3B · Qwen3 30B-A3B · Qwen2.5 14B · Qwen2.5-Coder 32B · Kimi-K2.7-Code · Kimi-K2.5 · Kimi-K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax-M2.5 · MiniMax-M2 · MiMo-V2.5 · Ornith-1.0 397B

Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.