llmrun
DeepSeekDeepSeek V4DeepseekV4ForCausalLM

DeepSeek V4 Flash 0731 — Hardware Requirements & GPU Compatibility

Chat

DeepSeek V4 Flash 0731 is a large-scale model from DeepSeek's V4 line, weighing in at roughly 304 billion parameters. At this scale it needs multi-GPU or server-class hardware to run; most users will reach it through a hosted endpoint rather than loading it locally on consumer equipment. It is tuned for general chat and instruction-following use. Its standout feature is a 1M token context window, among the largest available in an open-weight model, enabling it to process entire codebases, books, or long conversation histories in a single pass. Released under the permissive MIT license on July 31, 2026, DeepSeek V4 Flash 0731 is aimed at deployments where raw context length and model capacity matter more than local accessibility.

304.2B params · MoE27B active1049K contextMIT2.8M downloads4.1K likes184.7K quant downloads

DeepSeek V4 Flash 0731 runs on a 192 GB+ Mac or a datacenter GPU

Best local pick → Mac Pro M2 Ultra (192 GB) · Q4_K_M · 183 GB · ~26 tok/s

Macs from96 GB IQ2_XS · ~44 tok/s

Score 127.6#10 of 106 open#3 of 82 that fit ≤192 GBMIT

Not set up for it?

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

SOn your Instinct MI350X: Q4_K_M fits · 105 GB free · ~83 tok/s · up to 1M contextInstinct MI350X page →

llmrun Composite Score →

127.6

Benchmarks · tier chart ↓
Among 106 open modelsHow the Composite Score is built

Run DeepSeek V4 Flash 0731

Best fit for your Instinct MI350X. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended for your Instinct MI350X

Ollama
one command · needs Ollama installed
$ollama run hf.co/unsloth/DeepSeek-V4-Flash-0731-GGUF

Q4_K_M fits fully · 105.0 GB free · 16K context

Download: DeepSeek-V4-Flash-0731-Q4_K_M.gguf182.51 GBunsloth

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on B200 (192 GB) (9 GB headroom) · Q4_K_M

Generation speed
~181 tok/s
generation speed
Cost per 1M output tokens
$9.18
per 1M output tokens
Deployon RunPodBest valuefrom $5.98/hr (opens in new tab)

$5+ bonus for new users

Compare GPUs →
orDeploy on B200 · Vast.aifrom $9.93/hr (opens in new tab)

How Much VRAM Does DeepSeek V4 Flash 0731 Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn your device
84.0 GB84.3 GB2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality lossFits: 1M context · ~98 tok/s
91.6 GB91.9 GB2-bit · i-quant extra small — Importance-weighted 2-bit, extra smallFits: 1M context · ~97 tok/s
129.6 GB129.9 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 1M context · ~91 tok/s
148.6 GB149 GB3-bit medium — 3-bit medium quantizationFits: 1M context · ~88 tok/s
182.8 GB183.2 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 1M context · ~83 tok/s
217.1 GB217.4 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 1M context · ~79 tok/s
251.3 GB251.6 GB6-bit, very good — 6-bit quantization, very good qualityFits: 1M context · ~75 tok/s
304.5 GB304.8 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 304.7 GB
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

183.0GBat 16K context

Weights
182.5 GB
KV cache
0.2 GB
Overhead
0.3 GB

Fits Instinct MI350X · 105.0 GB free · ~83 tok/s

≥20 tok/s needs ≥530 GB/s · M3 Ultra ~27, M2 Ultra ~26

Or .

Which Hardware Can Run DeepSeek V4 Flash 0731?

Q4_K_M · 182.8 GB

DeepSeek V4 Flash 0731 (Q4_K_M) requires 182.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 238+ GB is recommended. Using the full 1049K context window can add up to 11.5 GB, bringing total usage to 194.3 GB. No consumer GPU has enough memory. 4 devices with unified memory can run DeepSeek V4 Flash 0731, including Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 256GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Consumer GPUs (up to 32 GB) and Macs up to 64 GB: too small for this model (needs ≥ 84.1 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →

How good is DeepSeek V4 Flash 0731?

The llmrun Score merges 21 public benchmark boards into a single figure, where 100 represents the average for open models.

Score vs VRAM in the ≤192 GB tier

  • DeepSeek V4 Flash 0731
  • Other models
  • Best Score for its VRAM

#3 of 82 that fit ≤192 GB

Each dot is a model at the best quant that fits ≤192 GB. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.

Full ≤192 GB ranking →

Benchmarks

The 6 boards that weigh most in the llmrun Score, of 21 with a result for this model; badges show who ran the test.

All 21 DeepSeek V4 Flash 0731 benchmarks

In the ≤192 GB class

82 models fit ≤192 GB

Same Score, only models that fit ≤192 GB at their best quant: the ranking a ≤192 GB owner actually chooses from.

  1. #1

    MiMo V2.6 Flash RLXiaomi

    131.9

    ~229 tok/s · 186.5 GB

  2. #2

    Step 5 PreviewStepFun

    128.0

    ~151 tok/s · 191.4 GB

  3. #3

    DeepSeek V4 Flash 0731DeepSeek

    127.6

    ~181 tok/s · 183.0 GB

  4. #4

    GLM 5.3 FlashZ.ai

    124.1

    ~228 tok/s · 185.1 GB

  5. #5

    Qwen3.8 27BAlibaba

    122.0

    ~299 tok/s · 17.9 GB

  6. #6

    Inkling SmallThinking Machines

    119.6

    ~399 tok/s · 162.7 GB

Full ≤192 GB ranking →B200 page →

Alternatives to DeepSeek V4 Flash 0731

DeepSeek V4 family · 13 models →

Official models with an llmrun Score, each answering one question; sizes are each model's default quant (usually Q4_K_M) with a 16K-token context.

Similar models

10
ModelScoreVRAMWhy it is similar
Qwen3.8 27BAlibaba122.017.9 GBsimilar score
Inkling SmallThinking Machines119.6162.7 GBsimilar score
Beam 1.0 501B A23Breflection119.5304 GBsimilar score
DeepSeek V4 FlashDeepSeek115.3175.1 GBsimilar score
Qwen3.5 397B A17BAlibaba112.8242.6 GBsimilar score
MiniMax M3MiniMax112.6258 GBsimilar score
MiniMax M2.5MiniMax111.8139.6 GBsame size
GLM 4.7Z.ai109.1217.9 GBsame size
Qwen3 235B A22B Thinking 2507Alibaba108.4142.9 GBsame size
MiMo V2.5Xiaomi108.3187.6 GBsame size
Fine-tunes & variants(6)

Specifications

Publisher
DeepSeek
Family
DeepSeek V4
Parameters
304.2B
Active parameters
27.4B per token
Architecture
DeepseekV4ForCausalLM
Context Length
1,048,576 tokens
Vocabulary Size
129,280
Release Date
2026-07-31
License
MIT

Resources

Frequently Asked Questions

How much VRAM does DeepSeek V4 Flash 0731 need?

DeepSeek V4 Flash 0731 requires 182.8 GB of VRAM at Q4_K_M, or 608.7 GB at BF16. Full 1049K context adds up to 11.5 GB (194.3 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 304.2B × 4.8 bits ÷ 8 = 182.5 GB

KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 11.8 GB (at full 1049K context)

VRAM usage by quantization

182.8 GB
194.3 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 5090 run DeepSeek V4 Flash 0731?

No — DeepSeek V4 Flash 0731 requires at least 84.0 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

What's the best quantization for DeepSeek V4 Flash 0731?

For DeepSeek V4 Flash 0731, Q4_K_M (182.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (217.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 84.0 GB.

VRAM requirement by quantization

IQ2_XXS
84.0 GB
IQ3_XXS
118.2 GB
IQ3_M
137.2 GB
Q4_K_M ★
182.8 GB
Q5_K_M
217.1 GB
BF16
608.7 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run DeepSeek V4 Flash 0731 on a Mac?

Yes — Mac Studio (M3 Ultra, 96GB) and 20 other Macs can run DeepSeek V4 Flash 0731, the smallest at IQ2_XS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 182.8 GB of usable unified memory (RAM minus macOS overhead), from Mac Pro M2 Ultra (192 GB).

Can I run DeepSeek V4 Flash 0731 locally?

Yes — DeepSeek V4 Flash 0731 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is DeepSeek V4 Flash 0731?

At Q4_K_M, DeepSeek V4 Flash 0731 can reach ~83 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)

Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.

Example: NVIDIA B200 → 16.4 GB active ÷ (8000 × 0.65) = 3.16 ms, plus 43 layers × 0.055 ms = 2.37 ms, so 1000 ÷ 5.53 ms = ~181 tok/s

Estimated speed at Q4_K_M (182.8 GB)

~181 tok/s
~181 tok/s
~83 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of DeepSeek V4 Flash 0731?

At Q4_K_M, the download is about 182.51 GB. The full-precision BF16 version is 608.36 GB. The smallest option (IQ2_XXS) is 83.65 GB.

Which GPUs can run DeepSeek V4 Flash 0731?

No single consumer GPU has enough VRAM to run DeepSeek V4 Flash 0731 at Q4_K_M (182.8 GB). Multi-GPU or professional hardware is required.

Which devices can run DeepSeek V4 Flash 0731?

4 devices with unified memory can run DeepSeek V4 Flash 0731 at Q4_K_M (182.8 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.