Local AI Wizard
DeepSeek / text + image

DeepSeek V4.1 Flash · max

EVIDENCE AT A GLANCE

Quality, size and local speed

LiveBench 2026-06-25 overall ↗Model card / primary source ↗
LiveBench · overall81.1/ 100

#1 among 22 evaluated open models in this release

Model-weight disk · Q4 estimate—No comparable size estimate
Planning memory · Q4 estimate—Includes planning allowance; not measured VRAM
Local speedNo exact measurementDo not infer speed from quality or memory
Quality · Published benchmark result; release and source linked aboveMemory · Planning estimate based on documented model size; not measured hardware fitLocal speed · No exact local measurement

Where it performs best

LiveBench 2026-06-25 · 0–100 ↗
Reasoning86.7
Coding80.0
Agentic Coding77.3
Mathematics93.3
Data Analysis79.3
Language81.2
IF70.0

LiveBench 2026-06-25 measures the named benchmark variant, not a local Q4 run. Scores were collected 2026-09-26; the seven categories share the same 0–100 scale. This is not the Artificial Analysis Intelligence Index. Q4 size covers only the counted weights; multimodal auxiliary components may add files.

SAME BENCHMARK RELEASE

Quality versus estimated Q4 weight size

Full ranking ↗

Reviewed language checkpoints with a LiveBench score and a parameter-based size estimate. The highlighted point is this model when both values are available.

506070809010100100010000Qwen3.8 27B · LiveBench 75.3 · Q4 ~16.9 GBQwen3.6 27B · LiveBench 64.0 · Q4 ~16.9 GBSmaug Mini · LiveBench 76.9 · Q4 ~17.5 GBGLM-5.3 Flash · LiveBench 71.6 · Q4 ~200.0 GBKimi K2.6 · thinking · LiveBench 70.5 · Q4 ~625.0 GBDeepSeek V4 Flash · LiveBench 65.5 · Q4 ~177.5 GBDeepSeek V4 Pro · LiveBench 71.6 · Q4 ~1000.0 GBKimi K2.7 Code · LiveBench 68.4 · Q4 ~625.0 GBMiniMax M3 · LiveBench 67.3 · Q4 ~267.5 GBKimi K3 · LiveBench 79.2 · Q4 ~1750.0 GBInkling · xhigh · LiveBench 71.9 · Q4 ~609.4 GBQwen3.8 Max · LiveBench 78.5 · Q4 ~1500.0 GBSmaug Agentic · LiveBench 79.5 · Q4 ~1750.0 GBDeepSeek V4 Pro · 0813 · LiveBench 77.4 · Q4 ~1000.0 GBNemotron 3 Ultra 550B A55B · LiveBench 67.4 · Q4 ~343.8 GB
Smaug Agentic79.5~1750.0 GBKimi K379.2~1750.0 GBQwen3.8 Max78.5~1500.0 GBDeepSeek V4 Pro · 081377.4~1000.0 GBSmaug Mini76.9~17.5 GB
Show 10 more modelsQwen3.8 27B75.3~16.9 GBInkling · xhigh71.9~609.4 GBGLM-5.3 Flash71.6~200.0 GBDeepSeek V4 Pro71.6~1000.0 GBKimi K2.6 · thinking70.5~625.0 GBKimi K2.7 Code68.4~625.0 GBNemotron 3 Ultra 550B A55B67.4~343.8 GBMiniMax M367.3~267.5 GBDeepSeek V4 Flash65.5~177.5 GBQwen3.6 27B64.0~16.9 GB

Horizontal axis: estimated Q4 model-weight disk size in decimal GB (log scale). Vertical axis: LiveBench overall / 100. This formula is not the published checkpoint size, runtime memory or a speed test. Models without both inputs are left out of this chart, not scored as zero.

The DeepSeek V4.1 Flash · max checkpoint is published by DeepSeek for language and reasoning. Its weights are available under MIT; that alone does not establish that its code and all components are open source.

When to consider it

Compare DeepSeek V4.1 Flash · max with other language and reasoning checkpoints using its linked publisher card and the LiveBench 2026-06-25 snapshot. This is quality evidence, not a local speed result.

Check before choosing

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.

What is documented

Weight license
MIT ↗
Task and modality
language and reasoning · text + image
Count and basis
Not verified
Context
1,000,000 tokens published for this model
Quality evidence
81.1 · LiveBench 2026-06-25 overall · source ↗
Runtime and precision
No local execution verified. Check the publisher's supported runtime and checkpoint precision; batch and context memory are not measured here.

Run locally: known and unknown

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.

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

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.

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