Skip to content
Local AI Wizard
Your machine
Theme

DeepSeek V4.1 Flash · max

DeepSeek · deepseek-ai/DeepSeek-V4.1-Flash

Weights license: MIT · code and components may use other terms

LiveBench · overall81.1 / 100#1 of 23 open models · 2026-06-25
Memory neededNo validated estimateQ4 heuristic · not measured
ParametersNot verifiedseparate components · 8B prefill / 16B decode active
Context1,000,000 tokensPublished for this model

Quality

Quality · Overall

LiveBench 2026-06-25 · 0–100 · higher is better · this model outlined, #1 of 23

  • Color = publisher
  • Memory under review

Source: LiveBench 2026-06-25 · collected 2026-10-18 · open models without a score are not drawn (no score ≠ 0)

LMArena · text · rating
1,476 ± 6Confidence interval 1,470–1,482 · 13,750 votes · rank 34 of the release · Arena dates this build 20260910, the day deepseek-ai/DeepSeek-V4.1-Flash was published on the Hub; (Max) is the max effort this entry namesLMArena 2026-10-22 · CC BY 4.0

LiveBench categories

This model's mean per category · 0–100

86.7ReasoningReasoning80.0CodingCoding77.3Agentic CodingAgentic Coding93.3MathematicsMathematics79.3Data AnalysisData Analysis81.2LanguageLanguage70.0IFIF

Source: LiveBench 2026-06-25 · collected 2026-10-18 · open models without a score are not drawn (no score ≠ 0)

Reported by the publisher

18 results · DeepSeek's model card · read 2026-10-25
GPQA Diamond (Pass@1)
90.9Reasoning
Codeforces (Rating)
3,471Reasoning
MathArena Apex (Pass@1)
65.6Reasoning
Terminal-Bench 2.1 (Pass@1)
90.6Agentic
Terminal-Bench 3.0 (Pass@1)
30.0Agentic
Terminal-Bench 4.0 (Pass@1)
31.2Agentic
DeepSWE v1.1 (Resolved)
74.2Agentic
ProgramBench (Almost@1)
20.3Agentic
Every reported result18
NL2Repo-Bench (Score)
64.0Agentic
CyberGym (Pass@1)
88.1Agentic
SEC-Bench Pro (Pass@1)
62.8Agentic
ExploitGym (Pass@1)
15.3Agentic
HLE w/ tools (Pass@1)
63.9Agentic
AutomationBench (Pass@1)
54.8Agentic
Agent's Last Exam (Pass@1)
31.8Agentic
Chartography w/ tools (Pass@1)
78.9Agentic
BabyVision w/ tools (Pass@1)
89.6Agentic
ZeroBench-main w/ tools (Pass@5)
49.0Agentic

Values as printed on the card, with the publisher's own settings (card section: Evaluation Results › Instruct Model › Comparison with frontier models (Max reasoning effort)); column “DS-V4.1-Flash”. Not comparable across publishers and not used in any ranking. Model card

Quality × memory

Not placed on quality × memory

There is no validated Q4 planning estimate for this checkpoint (its parameter basis does not allow one).

Runs on

No memory requirement to match

Without a parameter count with a known basis or a documented memory path, no hardware is grouped. Nothing is guessed.

DeepSeek V4.1 Flash · max is a text model from DeepSeek; this catalog has no verified parameter count for it, so no memory is estimated. It was released on September 10, 2026 and reads up to 1,000,000 tokens of context. No GGUF or MLX file for it was collected from the Hub, so this page lists no file sizes or run commands. It scores 81.1 overall in LiveBench 2026-06-25. Its LMArena text rating is 1,476 ± 6 (release 2026-10-22), a separate human-preference scale.

Plan another quantization or context

Consider it for

Compare DeepSeek V4.1 Flash · max using its publisher card and the LiveBench 2026-06-25 snapshot. This is quality evidence, not local speed.

Check first

This profile has no simplified memory estimate because the available size evidence is incomplete or includes separate components. Check the exact checkpoint, format and runtime before planning hardware.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

No validated memory estimate for this model and runtime.

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

Documented ways to run it

The model card points to another page without a command of its own

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

Versions to download
— No GGUF or MLX file collected from the Hub for this checkpoint
Publisher sampling defaults
— No Hub file facts collected for this checkpoint
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.

Task and modality
language and reasoning · text + image
Count and basis
Not verified
Context
1,000,000 tokens published for this model
Architecture
MoEdeepseek-ai/DeepSeek-V4.1-Flash model card (Hugging Face) · read 2026-10-09source
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
dba1be0a40aa45a94ad051997016db3960a90277
Architecture
DeepseekV41ForCausalLM
Library
transformers
Hub task tag
image-text-to-text
Formats
safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-09-10creation is not the model's release
Repository updated
2026-09-10a commit is not a release date
Hub downloads (30 days) · likes
1,640,989 · 4,734this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

552B backbone + 196B conditional Engram memory, plus other components. No simple total or local-memory estimate is published here.

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: 2026-10-18.