DeepSeek V4 Flash · 0731
DeepSeek · deepseek-ai/DeepSeek-V4-Flash-0731
Q4 file 136.7 GB (UD-IQ4_XS) · Weights license: MIT
Quality
Quality · Overall
LiveBench 2026-06-25 · 0–100 · higher is better · this model outlined, #12 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)
No result in LMArena 2026-10-22 Not in LMArena 2026-10-22
LiveBench categories
This model's mean per category · 0–100
Source: LiveBench 2026-06-25 · collected 2026-09-26 · open models without a score are not drawn (no score ≠ 0)
Reported by the publisher
- Terminal Bench 2.1
- 82.7
- NL2Repo
- 54.2
- Cybergym
- 76.7
- DeepSWE
- 54.4
- Toolathlon-Verified
- 70.3
- Agents' Last Exam
- 25.2
- AutomationBench Public
- 25.1
- DSBench-FullStack †
- 68.7
Every reported result
- DSBench-Hard †
- 59.6
Values as printed on the card, with the publisher's own settings (card section: Introduction); column “DeepSeek-V4-Flash-0731”. Not comparable across publishers and not used in any ranking. Model card
Run it
Run it
File UD-IQ4_XS · 136.7 GB · 4 parts · unsloth/DeepSeek-V4-Flash-0731-GGUF · What is Q4?
llama-server -hf unsloth/DeepSeek-V4-Flash-0731-GGUF:UD-IQ4_XS- Install llama.cpp
- Run the command above
- Ask at localhost:8080:
Explain what a context window is, in two sentences.
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 Flash · 0731 is a text model from DeepSeek with 304B parameters. It was released on July 31, 2026 and reads up to 1,048,576 tokens of context. This catalog does not turn its parameter count into a memory estimate; Check first says why. We collected 13 downloadable GGUF files from one publisher; the most downloaded GGUF source is unsloth's (701.8K downloads on the Hub). It scores 74.2 overall in LiveBench 2026-06-25.
Use this profile to inspect the named 0731 checkpoint and its available benchmark evidence before comparing larger language models.
The repository tensor count includes auxiliary components, so this page does not convert it into a local-memory requirement.
Versions to download
Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth (701.8K Hub downloads), at UD-IQ4_XS. Sizes are the Hub's published bytes. What is Q4?
GGUF · the only format collected
unsloth · 701.8K downloads
unsloth/DeepSeek-V4-Flash-0731-GGUF · UD-IQ4_XS/DeepSeek-V4-Flash-0731-UD-IQ4_XS-00001-of-00004.gguf · 136.7 GB
Run this file
llama-server -hf unsloth/DeepSeek-V4-Flash-0731-GGUF:UD-IQ4_XSlms get https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-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 versions
- Quantized versions
- 202
- Fine-tunes
- 38
- Adapters · merges
- 7 · 1
Browse them on the Hugging Face model tree · read 2026-10-23
Uncensored and abliterated versions
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.
29 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).
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.
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
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- 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-0731
- Task and modality
- language and reasoning · text
- Count and basis
- 304B · repository tensor elements
- Context
- 1,048,576 tokens published for this modeldeepseek-ai/DeepSeek-V4-Flash-0731 config.json (Hugging Face) · read 2026-10-09source
- Architecture
- MoEdeepseek-ai/DeepSeek-V4-Flash-0731 config.json (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 field
- Revision checked
- 7872f01b1d1fe23eabc4c98b48bffcef5a386062
- Architecture
- DeepseekV4ForCausalLM
- Library
- transformers
- Hub task tag
- text-generation
- Formats
- safetensors
- Access
- Open download
- Publisher kind
- Official
- Repository created
- 2026-07-31creation is not the model's release
- Repository updated
- 2026-08-01a commit is not a release date
- Hub downloads (30 days) · likes
- 4,112,191 · 4,088this repository only · read 2026-10-25
- Catalog state
- Hub config or weights found; no inventory benchmark link
Repository tensor count includes auxiliary components. This release references the DSpark architecture; unverified runtime specifications are omitted.
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.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · LiveBench 2026-06-25 overall
Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-09-26.