2026-09-13 22:45:43 +02:00
|
|
|
|
id: deepseek-ai__DeepSeek-V4-Flash-0731__strategic
|
2026-09-13 22:59:26 +02:00
|
|
|
|
status: collecting
|
2026-09-13 22:45:43 +02:00
|
|
|
|
name: DeepSeek-V4-Flash-0731
|
|
|
|
|
|
org: deepseek-ai
|
|
|
|
|
|
source:
|
|
|
|
|
|
kind: huggingface
|
|
|
|
|
|
url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
|
2026-09-14 00:17:15 +02:00
|
|
|
|
revision: 7872f01b1d1fe23eabc4c98b48bffcef5a386062
|
2026-09-13 22:45:43 +02:00
|
|
|
|
model_card_url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
|
|
|
|
|
|
project_url: https://www.deepseek.com/
|
|
|
|
|
|
paper_url: https://arxiv.org/abs/2606.19348
|
|
|
|
|
|
license:
|
|
|
|
|
|
spdx: MIT
|
|
|
|
|
|
url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
|
|
|
|
|
|
allows_offline_retention: true
|
|
|
|
|
|
allows_local_ops: true
|
|
|
|
|
|
allows_fine_tune: true
|
|
|
|
|
|
notes: "Official card: repository and weights MIT. Confirm at pin."
|
|
|
|
|
|
profile:
|
|
|
|
|
|
summary: "S-tier open MIT MoE — 284B base / ~13B active (304B with DSpark); not a 12B dense model."
|
|
|
|
|
|
original_source: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
|
|
|
|
|
|
use_cases:
|
|
|
|
|
|
- "Primary open-weight agentic / coding identity after Jul 2026"
|
|
|
|
|
|
- "Offline optionality if DeepSeek API access changes"
|
|
|
|
|
|
- "Future multi-GPU serve (vLLM DSpark / SGLang); not current R-spine"
|
|
|
|
|
|
- "Capability bar for daily briefs against closed frontier"
|
|
|
|
|
|
sweet_spots:
|
|
|
|
|
|
- "Best MIT-licensed open near-frontier that actually fits cheap Glacier (~167 GiB HF tree)"
|
|
|
|
|
|
- "Fits the €15/month Scaleway budget with room for K3"
|
|
|
|
|
|
- "Displaces DeepSeek-V3 as the collectable S1 identity"
|
|
|
|
|
|
not_ideal_for:
|
|
|
|
|
|
- "Current single-consumer-GPU daily ops (use R spine / Qwen3.8-27B)"
|
|
|
|
|
|
- "Treating 'Flash' as a 12B dense model (that reading was an executor error)"
|
|
|
|
|
|
capability_notes: >
|
|
|
|
|
|
Official V4-Flash release (2026-07-31). Same structure as
|
|
|
|
|
|
DeepSeek-V4-Flash-DSpark (speculative decoding module attached).
|
|
|
|
|
|
HF card reports 304B params (284B base + draft). ~13B active.
|
|
|
|
|
|
1M context. Terminal Bench 2.1 82.7. HF tree listed ~167 GB.
|
|
|
|
|
|
Automated briefs 2026-08-04…14 repeatedly called this a 12B dense
|
|
|
|
|
|
consumer-GPU model and once claimed it was already collected. It
|
|
|
|
|
|
was not. Size class is S, not R.
|
|
|
|
|
|
swot:
|
|
|
|
|
|
strengths:
|
|
|
|
|
|
- "MIT, official org, actually downloadable"
|
|
|
|
|
|
- "Near-frontier agentic scores at ~13B active"
|
|
|
|
|
|
- "Footprint (~167 GiB) is cheap on Glacier and was always inside the old 850 GiB quota"
|
|
|
|
|
|
weaknesses:
|
|
|
|
|
|
- "Serve needs multi-GPU / high unified memory, not T1–T2"
|
|
|
|
|
|
- "Executor hallucinated it as 12B for two weeks — catalog must stay the authority"
|
|
|
|
|
|
opportunities:
|
|
|
|
|
|
- "First S pull onto Scaleway (FI-WP-0004-T09)"
|
|
|
|
|
|
- "Compressed / GGUF community packs exist if we want a later R experiment (not a substitute for the official tree)"
|
|
|
|
|
|
threats:
|
|
|
|
|
|
- "Successor V4.x could land while we still have no object on disk"
|
|
|
|
|
|
- "Quota-era deferral already cost a month of optionality"
|
|
|
|
|
|
size:
|
2026-09-14 00:17:15 +02:00
|
|
|
|
total_bytes: 166898547054
|
|
|
|
|
|
total_human: "166.9 GB / 155.4 GiB; 67 selected files at pinned commit, HF metadata 2026-09-14"
|
2026-09-13 22:45:43 +02:00
|
|
|
|
hardware_class:
|
|
|
|
|
|
min_vram_gb_q4: 0
|
|
|
|
|
|
min_vram_gb_fp16: 0
|
|
|
|
|
|
notes: "Beyond current lab run envelope (T3–T4). Community 2-bit reports exist for 128 GB unified memory; not an R-spine claim."
|
|
|
|
|
|
axes: [A, B, D]
|
|
|
|
|
|
priority: high
|
|
|
|
|
|
collection:
|
|
|
|
|
|
approved_by: "grok"
|
|
|
|
|
|
approved_at: "2026-09-13"
|
|
|
|
|
|
downloaded_at: null
|
|
|
|
|
|
downloaded_by: ""
|
|
|
|
|
|
storage_path: ""
|
|
|
|
|
|
brief_refs:
|
|
|
|
|
|
- briefs/2026/08/2026-08-03.md
|
|
|
|
|
|
- briefs/2026/09/2026-09-13.md
|
|
|
|
|
|
- docs/decisions/2026-09-13-scaleway-object-reserve.md
|
|
|
|
|
|
reason: "S1 collectable — strongest MIT open MoE that fits the Scaleway euro budget; first pull after bucket create."
|
|
|
|
|
|
tags: [tier-s, strategic, moe, mit, beyond-run-envelope]
|
|
|
|
|
|
companions: []
|
|
|
|
|
|
notes: >
|
|
|
|
|
|
Do not confuse with a 12B dense checkpoint. There is no
|
|
|
|
|
|
deepseek-ai/DeepSeek-V4-Flash-0731-12B. Pull the official card repo.
|
|
|
|
|
|
Storage class at upload: strategic/ → Glacier.
|
|
|
|
|
|
history:
|
|
|
|
|
|
- at: "2026-08-03"
|
|
|
|
|
|
event: nominated
|
|
|
|
|
|
by: grok
|
|
|
|
|
|
detail: "Catch-up brief named V4-Flash-0731 as mid-tier open value leader."
|
|
|
|
|
|
- at: "2026-08-04"
|
|
|
|
|
|
event: misidentified
|
|
|
|
|
|
by: rein-aharness
|
|
|
|
|
|
detail: "Automated briefs treated it as 12B dense; never cataloged; 08-07 claimed on-disk collection that did not happen."
|
|
|
|
|
|
- at: "2026-09-13"
|
|
|
|
|
|
event: approved
|
|
|
|
|
|
by: grok
|
|
|
|
|
|
detail: "Corrected to 304B-class MoE ~167 GiB MIT. Approved for Scaleway Glacier once FI-WP-0004-T08 bucket exists."
|
2026-09-13 22:59:34 +02:00
|
|
|
|
- at: "2026-09-13"
|
|
|
|
|
|
event: collecting
|
|
|
|
|
|
by: grok
|
|
|
|
|
|
detail: "T08 bucket live. snapshot_download + Glacier upload started on workstation staging /home/worsch/vault/freedom-intelligence."
|
2026-09-14 00:17:15 +02:00
|
|
|
|
- at: "2026-09-14"
|
|
|
|
|
|
event: collecting
|
|
|
|
|
|
by: codex
|
|
|
|
|
|
detail: "Replaced WSL snapshot staging with diskless Railiance service fi-reserve-collect. 64 MiB parts, 512 MiB memory cap, no swap. Source pinned to 7872f01b1d1fe23eabc4c98b48bffcef5a386062; 67 selected files / 166898547054 bytes. Destination strategic/deepseek-ai__DeepSeek-V4-Flash-0731/<commit>/. Complete manifest pending; not collected or restore-verified."
|
