Skip to content
Local AI Wizard
Your machine
Theme

DeepSeek V4 Flash

DeepSeek · deepseek-ai/DeepSeek-V4-Flash

Text & chat

Q4 file 137.9 GB (UD-IQ4_XS) · runs well from 512 GB · Weights license: MIT

LiveBench · overall65.5 / 100#21 of 22 open models · 2026-06-25
Memory needed~213 GBQ4 weights + working room, before the machine's reserve
Parameters284 Bmanufacturer specification · 13B active
Context1,048,576 tokensPublished for this model

Quality

Quality · Overall

LiveBench 2026-06-25 · 0–100 · higher is better · this model outlined, #21 of 22

  • Color = publisher
  • Memory under review

Source: LiveBench 2026-06-25 · collected 2026-09-26 · open models without a score are not drawn (no score ≠ 0)

LMArena · text · rating
1,436 ± 4Confidence interval 1,432–1,440 · 51,982 votes · rank 105 of the releaseLMArena 2026-10-22 · CC BY 4.0

LiveBench categories

This model's mean per category · 0–100

70.6ReasoningReasoning69.2CodingCoding37.6Agentic CodingAgentic Coding79.6MathematicsMathematics68.0Data AnalysisData Analysis70.1LanguageLanguage63.1IFIF

Source: LiveBench 2026-06-25 · collected 2026-09-26 · open models without a score are not drawn (no score ≠ 0)

Reported by the publisher

61 results · DeepSeek's model card · read 2026-10-25
MMLU-Pro (EM)
83.0V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
SimpleQA-Verified (Pass@1)
23.1V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
Chinese-SimpleQA (Pass@1)
71.5V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
GPQA Diamond (Pass@1)
71.2V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
HLE (Pass@1)
8.1V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
LiveCodeBench (Pass@1)
55.2V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
HMMT 2026 Feb (Pass@1)
40.8V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
IMOAnswerBench (Pass@1)
41.9V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
Every reported result61
Apex (Pass@1)
1.0V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
Apex Shortlist (Pass@1)
9.3V4-Flash Non-Think · Knowledge & Reasoning · thinking mode
MRCR 1M (MMR)
37.5V4-Flash Non-Think · Long Context · thinking mode
CorpusQA 1M (ACC)
15.5V4-Flash Non-Think · Long Context · thinking mode
Terminal Bench 2.0 (Acc)
49.1V4-Flash Non-Think · Agentic · thinking mode
SWE Verified (Resolved)
73.7V4-Flash Non-Think · Agentic · thinking mode
SWE Pro (Resolved)
49.1V4-Flash Non-Think · Agentic · thinking mode
SWE Multilingual (Resolved)
69.7V4-Flash Non-Think · Agentic · thinking mode
MCPAtlas (Pass@1)
64.0V4-Flash Non-Think · Agentic · thinking mode
Toolathlon (Pass@1)
40.7V4-Flash Non-Think · Agentic · thinking mode
MMLU-Pro (EM)
86.4V4-Flash High · Knowledge & Reasoning
SimpleQA-Verified (Pass@1)
28.9V4-Flash High · Knowledge & Reasoning
Chinese-SimpleQA (Pass@1)
73.2V4-Flash High · Knowledge & Reasoning
GPQA Diamond (Pass@1)
87.4V4-Flash High · Knowledge & Reasoning
HLE (Pass@1)
29.4V4-Flash High · Knowledge & Reasoning
LiveCodeBench (Pass@1)
88.4V4-Flash High · Knowledge & Reasoning
Codeforces (Rating)
2,816V4-Flash High · Knowledge & Reasoning
HMMT 2026 Feb (Pass@1)
91.9V4-Flash High · Knowledge & Reasoning
IMOAnswerBench (Pass@1)
85.1V4-Flash High · Knowledge & Reasoning
Apex (Pass@1)
19.1V4-Flash High · Knowledge & Reasoning
Apex Shortlist (Pass@1)
72.1V4-Flash High · Knowledge & Reasoning
MRCR 1M (MMR)
76.9V4-Flash High · Long Context
CorpusQA 1M (ACC)
59.3V4-Flash High · Long Context
Terminal Bench 2.0 (Acc)
56.6V4-Flash High · Agentic
SWE Verified (Resolved)
78.6V4-Flash High · Agentic
SWE Pro (Resolved)
52.3V4-Flash High · Agentic
SWE Multilingual (Resolved)
70.2V4-Flash High · Agentic
BrowseComp (Pass@1)
53.5V4-Flash High · Agentic
HLE w/ tools (Pass@1)
40.3V4-Flash High · Agentic
MCPAtlas (Pass@1)
67.4V4-Flash High · Agentic
Toolathlon (Pass@1)
43.5V4-Flash High · Agentic
MMLU-Pro (EM)
86.2V4-Flash Max · Knowledge & Reasoning
SimpleQA-Verified (Pass@1)
34.1V4-Flash Max · Knowledge & Reasoning
Chinese-SimpleQA (Pass@1)
78.9V4-Flash Max · Knowledge & Reasoning
GPQA Diamond (Pass@1)
88.1V4-Flash Max · Knowledge & Reasoning
HLE (Pass@1)
34.8V4-Flash Max · Knowledge & Reasoning
LiveCodeBench (Pass@1)
91.6V4-Flash Max · Knowledge & Reasoning
Codeforces (Rating)
3,052V4-Flash Max · Knowledge & Reasoning
HMMT 2026 Feb (Pass@1)
94.8V4-Flash Max · Knowledge & Reasoning
IMOAnswerBench (Pass@1)
88.4V4-Flash Max · Knowledge & Reasoning
Apex (Pass@1)
33.0V4-Flash Max · Knowledge & Reasoning
Apex Shortlist (Pass@1)
85.7V4-Flash Max · Knowledge & Reasoning
MRCR 1M (MMR)
78.7V4-Flash Max · Long Context
CorpusQA 1M (ACC)
60.5V4-Flash Max · Long Context
Terminal Bench 2.0 (Acc)
56.9V4-Flash Max · Agentic
SWE Verified (Resolved)
79.0V4-Flash Max · Agentic
SWE Pro (Resolved)
52.6V4-Flash Max · Agentic
SWE Multilingual (Resolved)
73.3V4-Flash Max · Agentic
BrowseComp (Pass@1)
73.2V4-Flash Max · Agentic
HLE w/ tools (Pass@1)
45.1V4-Flash Max · Agentic
MCPAtlas (Pass@1)
69.0V4-Flash Max · Agentic
GDPval-AA (Elo)
1,395V4-Flash Max · Agentic
Toolathlon (Pass@1)
47.8V4-Flash Max · Agentic
Across DeepSeek V4 sizes40 shared results · same publisher and settings
DeepSeek V4: results the publisher reports for each size under the same settings
Benchmark (publisher settings)Flash 284BPro 1.6T
MMLU-Pro (EM) · Knowledge & Reasoning83.082.9
SimpleQA-Verified (Pass@1) · Knowledge & Reasoning23.145.0
Chinese-SimpleQA (Pass@1) · Knowledge & Reasoning71.575.8
GPQA Diamond (Pass@1) · Knowledge & Reasoning71.272.9
HLE (Pass@1) · Knowledge & Reasoning8.17.7
LiveCodeBench (Pass@1) · Knowledge & Reasoning55.256.8
HMMT 2026 Feb (Pass@1) · Knowledge & Reasoning40.831.7
IMOAnswerBench (Pass@1) · Knowledge & Reasoning41.935.3
Apex (Pass@1) · Knowledge & Reasoning1.00.4
Apex Shortlist (Pass@1) · Knowledge & Reasoning9.39.2
MRCR 1M (MMR) · Long Context37.544.7
CorpusQA 1M (ACC) · Long Context15.535.6
Terminal Bench 2.0 (Acc) · Agentic49.159.1
SWE Verified (Resolved) · Agentic73.773.6
SWE Pro (Resolved) · Agentic49.152.1
SWE Multilingual (Resolved) · Agentic69.769.8
MCPAtlas (Pass@1) · Agentic64.069.4
Toolathlon (Pass@1) · Agentic40.746.3
MMLU-Pro (EM) · Knowledge & Reasoning86.487.1
SimpleQA-Verified (Pass@1) · Knowledge & Reasoning28.946.2
Chinese-SimpleQA (Pass@1) · Knowledge & Reasoning73.277.7
GPQA Diamond (Pass@1) · Knowledge & Reasoning87.489.1
HLE (Pass@1) · Knowledge & Reasoning29.434.5
LiveCodeBench (Pass@1) · Knowledge & Reasoning88.489.8
Codeforces (Rating) · Knowledge & Reasoning2,8162,919
HMMT 2026 Feb (Pass@1) · Knowledge & Reasoning91.994.0
IMOAnswerBench (Pass@1) · Knowledge & Reasoning85.188.0
Apex (Pass@1) · Knowledge & Reasoning19.127.4
Apex Shortlist (Pass@1) · Knowledge & Reasoning72.185.5
MRCR 1M (MMR) · Long Context76.983.3
CorpusQA 1M (ACC) · Long Context59.356.5
Terminal Bench 2.0 (Acc) · Agentic56.663.3
SWE Verified (Resolved) · Agentic78.679.4
SWE Pro (Resolved) · Agentic52.354.4
SWE Multilingual (Resolved) · Agentic70.274.1
BrowseComp (Pass@1) · Agentic53.580.4
HLE w/ tools (Pass@1) · Agentic40.344.7
MCPAtlas (Pass@1) · Agentic67.474.2
Toolathlon (Pass@1) · Agentic43.549.0
GDPval-AA (Elo) · Agentic1,3951,554

Values as printed on the card, with the publisher's own settings (card section: Evaluation Results › Instruct Model › Comparison across Modes). Not comparable across publishers and not used in any ranking. Model card

Run it

Run it

File UD-IQ4_XS · 137.9 GB · 4 parts · unsloth/DeepSeek-V4-Flash-GGUF · What is Q4?

Measured 39 tok/s · FP8 · 1 machine · Lambda inference models · all rows

llama-server -hf unsloth/DeepSeek-V4-Flash-GGUF:UD-IQ4_XS
  1. Install llama.cpp
  2. Run the command above
  3. Ask at localhost:8080: Explain what a context window is, in two sentences.

Quality × memory

Quality × memory

LiveBench 2026-06-25 overall vs. Q4 planning memory (log scale) · 18 open models

  • This model
  • Color = publisher
60708081632641282565121,0242,0484,096Memory needed · Q4 · model only (GB, log)LiveBenchSmaug AgenticQwen3.8 MaxDeepSeek V4 Pro · 0813Smaug MiniDeepSeek V4 Flash

Memory = the model's own figure: parameters × 0.625 bytes + 20% working room, before any machine's reserve; with a chosen machine, the total there with its reserve (25% of memory, 2 to 8 GB; 2 GB per graphics card). An estimate, not measured VRAM. LiveBench 2026-06-25

Runs on

Fast memory holds it 1

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Within memory, outside the fast part 1

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

One memory tier short 9

The same machines with the next memory size up would hold it in fast memory.

Show all 9

DeepSeek V4 Flash is a text model from DeepSeek with 284B parameters, 13B of them active per token (mixture of experts). It was released on April 24, 2026 and reads up to 1,048,576 tokens of context. Its Q4 weights plus working room come to about 213 GB before the machine's reserve; the smallest reference machine whose fast memory holds that is Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unified (~221 GB with its reserve). We collected 16 downloadable GGUF and MLX files from 2 publisher sources; the most downloaded GGUF source is unsloth's (234.5K downloads on the Hub). It scores 65.5 overall in LiveBench 2026-06-25. Its LMArena text rating is 1,436 ± 4 (release 2026-10-22), a separate human-preference scale.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.

On the reference machines

DeepSeek V4 Flash on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~215 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 16 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~217 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 24 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~219 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 32 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~221 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M5 Pro · 64 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~221 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac Studio M5 Max · 128 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~221 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itUD-IQ4_XSGGUF · 137.9 GB · needs ~174 GBKV-cache formula for this architecture not reviewed~221 GBFast memory holds itUD-IQ4_XSGGUF · 137.9 GB · needs ~174 GBKV-cache formula for this architecture not reviewed
RTX 4060 · 8 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~215 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 3060 · 12 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~215 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5080 · 16 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~215 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 4090 · 24 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~215 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5090 · 32 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~215 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
DGX H100 · 8 × 80 GBFast memory holds itUD-IQ4_XSGGUF · 137.9 GB · needs ~182 GBKV-cache formula for this architecture not reviewed~229 GBFast memory holds itUD-IQ4_XSGGUF · 137.9 GB · needs ~182 GBKV-cache formula for this architecture not reviewed

The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.

Plan another quantization or context

Consider it for

Compare DeepSeek V4 Flash using its publisher card and the LiveBench 2026-06-25 snapshot. This is quality evidence, not local speed.

Check first

The Q4 weights plus working room come to about 213 GB from 284B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Versions to download

Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth (234.5K Hub downloads), at UD-IQ4_XS. On a Mac it opens on the most downloaded MLX source. Sizes are the Hub's published bytes. What is Q4?

unsloth · 234.5K downloads

unsloth/DeepSeek-V4-Flash-GGUF · UD-IQ4_XS/DeepSeek-V4-Flash-UD-IQ4_XS-00001-of-00004.gguf · 137.9 GB

Run this file

llama-server -hf unsloth/DeepSeek-V4-Flash-GGUF:UD-IQ4_XS
lms get https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF
  • Ollama: Ollama's documented hf.co form covers single-file GGUFs; this file has 4 parts
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)

Fine-tunes, adapters and other versions28 fine-tunes
Quantized versions
134
Fine-tunes
28
Adapters · merges
4 · 0

Browse them on the Hugging Face model tree · read 2026-10-23

Uncensored and abliterated versions15

Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.

15 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).

Measured speed

Tokens per second by machine

Output tok/s · 1 machine · every row in the table · What is a token?

DGX H100, 39 per user (32 concurrent) · FP8 (sgl-project/DeepSeek-V4-Flash-FP8)39.0
Measured speed
DGX H100NVIDIA HGX H100 · 8× H100 80 GB (TP=8) · Lambda Cloud39 per user (32 concurrent)FP8 (sgl-project/DeepSeek-V4-Flash-FP8)8192 / 1024 · 32 concurrent requests; per-user output rate with EAGLE speculative decoding, not a single-stream figure (aggregate 1,262 tok/s)SGLang with EAGLE speculative decoding (docker lmsysorg/sglang:deepseek-v4-hopper)docker lmsysorg/sglang:deepseek-v4-hopper (no SGLang version number); SGLANG_DSV4_FP4_EXPERTS=0; --tp 8; --mem-fraction-static 0.85; --speculative-algo EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4; --chunked-prefill-size 4096sgl-project/DeepSeek-V4-Flash-FP8 (FP8 repack, about 284 GB); not deepseek-ai/DeepSeek-V4-Flash

Source: Lambda inference models · DeepSeek-V4-Flash (vendor benchmark) (checked 2026-10-09) · SGLang with EAGLE speculative decoding (docker lmsysorg/sglang:deepseek-v4-hopper) · docker lmsysorg/sglang:deepseek-v4-hopper (no SGLang version number); SGLANG_DSV4_FP4_EXPERTS=0; --tp 8; --mem-fraction-static 0.85; --speculative-algo EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4; --chunked-prefill-size 4096 · not estimated

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Evidence level: Generic estimate only; no execution reproduced by this site.

Publisher sampling defaults
temperature 1 · top_p 1generation_config.json · read 2026-10-23source
Chat template markers
— Chat template not read for this checkpoint
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / version
deepseek-ai/DeepSeek-V4-Flash
Task and modality
language and reasoning · text
Count and basis
284B · manufacturer specification · 13B active
Context
1,048,576 tokens published for this model
Architecture
MoE
Released
Change Log | DeepSeek API Docs · read 2026-10-09source
Runtime and precision
No local execution verified.
Commercial use
Allowed MIT license text (SPDX) · read 2026-10-18license text
Every stored field11 fields
Revision checked
60d8d70770c6776ff598c94bb586a859a38244f1
Architecture
DeepseekV4ForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-04-22creation is not the model's release
Repository updated
2026-06-22a commit is not a release date
Hub downloads (30 days) · likes
936,089 · 2,344this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-09-26.