How much memory do I need to run DeepSeek-V4-Flash (UD-IQ1_S)?

The file size is 82.5 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 83.4 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.

Does DeepSeek-V4-Flash run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?

8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: no quantization fits (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).

What is the command to run DeepSeek-V4-Flash with Ollama?

Run "ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-IQ1_S" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.

deepseek-ai

DeepSeek-V4-Flash

Parameters: 284.3B
Max context length: 1,048,576
Architecture: deepseek4
License: Commercial OK

Base model: deepseek-ai/DeepSeek-V4-Flash
License: mit
llama.cpp: b9840+

Memory needed to run UD-IQ1_S at 8K tokens

83.4 GB Estimated

File size 82.5 GB Measured

VRAM it fits in (rough guide)

8 GB does not fit
12 GB does not fit
16 GB does not fit
24 GB does not fit
32 GB does not fit
48 GB does not fit

See devices and models for 96 GB

Macs cap how much memory the GPU can use, so leave headroom in unified memory.

Data as of Oct 1, 2026

About DeepSeek-V4-Flash

DeepSeek-V4-Flash is a GGUF model based on deepseek-ai/DeepSeek-V4-Flash on Hugging Face. GGUF files are published by unsloth/DeepSeek-V4-Flash-GGUF. It has about 284.3B parameters, the deepseek4 architecture, a maximum context length of 1,048,576 tokens (values written in the GGUF).

There are 13 quantizations, with file sizes from 82.5 GB (UD-IQ1_S) to 162 GB (UD-Q8_K_XL) (actual sizes on Hugging Face).

Running UD-IQ1_S (82.5 GB) with an 8,192-token context needs an estimated 83.4 GB of memory, and an estimated 83.6 GB at 32,768 tokens. For 8,192 tokens, a GPU with 96 GB or more of VRAM, or a Mac with 96 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom).

The original model is licensed under MIT License, which allows commercial use (keep the license text and copyright notice when redistributing). Check the original license for the terms of use.

File size and estimated memory per quantization

Up to 8 GB
Up to 16 GB
Up to 24 GB
Up to 48 GB
Up to 128 GB
More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization	Quality guide	KLD (no imatrix)	KLD (imatrix)	Size (Llama-3-8B)
Q8_0	Nearly identical	0.0014	-	7.96 GiB
Q6_K	Very small	0.0055	-	6.14 GiB
Q5_K_M	Very small	0.0108	-	5.33 GiB
Q5_K_S	Small	0.0166	-	5.21 GiB
Q5_1	Small	0.0180	-	5.65 GiB
Q5_0	Small	0.0222	-	5.21 GiB
Q4_K_M	Small	0.0313	0.0282	4.58 GiB
Q4_K_S	Medium	0.0431	0.0320	4.37 GiB
IQ4_NL	Small	-	0.0357	4.35 GiB
IQ4_XS	Small	-	0.0363	4.14 GiB
Q4_1	Medium	0.0717	-	4.78 GiB
Q4_0	Medium	0.0719	-	4.34 GiB
Q3_K_L	Medium	0.0872	0.0731	4.03 GiB
Q3_K_M	Medium	0.1019	0.0844	3.74 GiB
IQ3_M	Medium	-	0.1025	3.53 GiB
IQ3_S	Medium	-	0.1113	3.42 GiB
IQ3_XS	Large	-	0.1387	3.28 GiB
IQ3_XXS	Large	-	0.1836	3.05 GiB
Q3_K_S	Large	0.2282	0.1998	3.41 GiB
IQ2_M	Large	-	0.3260	2.74 GiB
Q2_K	Very large	0.4451	0.3322	2.96 GiB
Q2_K_S	Very large	-	0.4034	2.96 GiB
IQ2_S	Very large	-	0.4392	2.56 GiB
IQ2_XS	Very large	-	0.5463	2.43 GiB
IQ2_XXS	Very large	-	0.8120	2.24 GiB
IQ1_M	Very large	-	1.3931	2.01 GiB
IQ1_S	Very large	-	2.2546	1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

unsloth/DeepSeek-V4-Flash-GGUF

Converted and published by a third party About this label

Last checked: Oct 1, 2026

Architecture: deepseek4; llama.cpp b9840 and later
Parameters: 284.3B
Max context length: 1,048,576
License: mit Commercial OK

File size and memory per quantization for DeepSeek-V4-Flash (unsloth/DeepSeek-V4-Flash-GGUF)
Quantization	File size Measured	Quality guide	4,096	8,192	16,384	32,768	65,536	131,072	262,144	1,048,576 max
UD-IQ1_S (3 parts)	82.5 GB	-	83.4 GB	83.4 GB	83.5 GB	83.6 GB	83.8 GB	84.3 GB	85.2 GB	90.6 GB
UD-IQ1_M (3 parts)	86.9 GB	-	87.8 GB	87.8 GB	87.9 GB	88.0 GB	88.2 GB	88.7 GB	89.6 GB	95.0 GB
UD-IQ2_XXS (3 parts)	90.9 GB	-	91.7 GB	91.8 GB	91.8 GB	91.9 GB	92.2 GB	92.6 GB	93.5 GB	98.9 GB
UD-IQ2_M (3 parts)	90.9 GB	-	91.8 GB	91.8 GB	91.9 GB	92.0 GB	92.2 GB	92.7 GB	93.6 GB	99.0 GB
UD-Q2_K_XL (3 parts)	96.8 GB	-	97.7 GB	97.7 GB	97.8 GB	97.9 GB	98.1 GB	98.6 GB	99.5 GB	105 GB
UD-IQ3_XXS (4 parts)	103 GB	-	104 GB	104 GB	104 GB	104 GB	104 GB	105 GB	106 GB	111 GB
UD-IQ3_S (4 parts)	117 GB	-	118 GB	118 GB	118 GB	118 GB	119 GB	119 GB	120 GB	125 GB
UD-Q3_K_M (4 parts)	129 GB	-	130 GB	130 GB	130 GB	130 GB	131 GB	131 GB	132 GB	137 GB
UD-Q3_K_XL (4 parts)	129 GB	-	130 GB	130 GB	130 GB	131 GB	131 GB	131 GB	132 GB	138 GB
UD-IQ4_NL (4 parts)	138 GB	-	139 GB	139 GB	139 GB	139 GB	139 GB	140 GB	141 GB	146 GB
UD-IQ4_XS (4 parts)	138 GB	-	139 GB	139 GB	139 GB	139 GB	139 GB	140 GB	141 GB	146 GB
UD-Q4_K_XL (5 parts)	155 GB	-	156 GB	156 GB	156 GB	156 GB	156 GB	157 GB	158 GB	163 GB
UD-Q8_K_XL (5 parts)	162 GB	-	163 GB	163 GB	163 GB	163 GB	163 GB	164 GB	165 GB	170 GB

Ollama  ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-IQ1_S

llama.cpp  llama-server -hf unsloth/DeepSeek-V4-Flash-GGUF:UD-IQ1_S

Third-party evaluations

Values from other organizations for the original model before quantization. Not this site's own rating. Values are for the original model before quantization. GGUF quantization (especially small quantizations) can lower performance.

Human preference (LMArena)

1,436 1,432–1,440

deepseek-v4-flash · 51,368 votes · Values as of Nov 9, 2026

Source: LMArena (CC BY 4.0). Original leaderboard · See in ranking

Capabilities (Epoch AI)

146.9 143.6–150.2

DeepSeek-V4-Flash · Values as of Apr 24, 2026

Source: Epoch Capabilities Index (Epoch AI) (CC BY 4.0). Original leaderboard · See in ranking

License and commercial use

MIT License Commercial OK

Allows commercial use, modification and redistribution. When redistributing, keep the copyright notice and license text.

Based on the license on the original model's Hugging Face page. Original license text (checked Oct 18, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Mainline llama.cpp can load this model's format (deepseek4) from b9840 (Jun 29, 2026) onward. Ollama and LM Studio bundle llama.cpp internally, so an older app fails to load it with errors such as "unknown model architecture". If that happens, update the app.

Example commands using UD-IQ1_S. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-IQ1_S

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf unsloth/DeepSeek-V4-Flash-GGUF:UD-IQ1_S

LM Studio

Paste unsloth/DeepSeek-V4-Flash-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run DeepSeek-V4-Flash (UD-IQ1_S)?: The file size is 82.5 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 83.4 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can DeepSeek-V4-Flash be used commercially?: The original model's license is MIT License (Commercial use allowed).Allows commercial use, modification and redistribution. When redistributing, keep the copyright notice and license text. Check the original license text before deciding.
Does DeepSeek-V4-Flash run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?: 8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: no quantization fits (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run DeepSeek-V4-Flash with Ollama?: Run "ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-IQ1_S" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.