ModelBrief · Edge0-145B · Topic Page
Last updated Nov 20, 2026

Edge0-145B vs Qwen3.8-Flash-Next and DeepSeek

ModelBrief · Published 2026-11-20 · Fact-check 2026-11-20 · Reference: Edge0 official blog, Hugging Face model cards, GitHub Edge0-AI/Edge0

The most important thing about Edge0-145B is often buried under the headline: it is not a from-scratch base model but a derivative of Alibaba's Qwen3.8-Flash-Next — the model card's metadata names base_model as Qwen/Qwen3.8-Flash-Next, with the routed experts in all 48 layers rebuilt as latent MoE and post-training afterwards on Edge0's own data. The right question is not "how strong is it" but "what did the rebuild and post-training buy over the base". Every score below is vendor-reported (Edge0 internal evaluations) with no independent verification as of Nov 20, 2026.

vs the base, Qwen3.8-Flash-Next: two big wins, three small losses

BenchmarkEdge0-145BQwen3.8-Flash-NextDelta
DeepSWE 1.164.658.7+5.9
Terminal-Bench 2.186.5283.3+3.22
HLE35.435.9−0.5
GPQA-Diamond90.491.7−1.3
IFBench80.681.3−0.7
AA-LCR79.379.1+0.2
Mean (6)72.871.7+1.1

What the rebuild bought is direction, not breadth. DeepSWE and Terminal-Bench are agent and terminal-coding tasks — exactly Edge0-145B's positioning — and together they contribute +9.1 points, the whole of the rebuild's gain. HLE, GPQA-Diamond and IFBench — knowledge and instruction-following — all trail, by −2.5 points combined, which suggests the post-training data mix pushed capability toward coding while giving back a little general ability. AA-LCR is essentially level. The +1.1 mean is the net of those two forces.

There is also a structural difference the scores do not capture: the base Qwen3.8-Flash-Next is a cloud model, while Edge0-145B was rewritten for on-device use — natively trained at 4 bits, latent MoE, a three-tier memory pipeline, 256K context. The score lead is only 1.1 points, but the deployment shape is entirely different: one needs a data centre, the other one consumer GPU plus a large helping of RAM. The reason to buy Edge0-145B is first "a 145B that runs locally" — the score lead is secondary.

vs DeepSeek-V4-Flash: ahead on coding, split on knowledge

BenchmarkEdge0-145BDeepSeek-V4-Flash-0731Delta
DeepSWE 1.164.654.4+10.2
Terminal-Bench 2.186.5282.7+3.82
HLE35.433.8+1.6
GPQA-Diamond90.490.8−0.4
IFBench80.679.2+1.4
AA-LCR79.379.7−0.4
Mean (6)72.870.1+2.7

The mean lead over DeepSeek-V4-Flash is +2.7, larger than the +1.1 over the base — but the shape is the same: the lead concentrates on DeepSWE (+10.2) and Terminal-Bench (+3.82), while GPQA-Diamond and AA-LCR still trail. In other words, Edge0-145B is "strong on coding, level on knowledge" against everyone — not an artefact of the comparison model, but the shape of its own capability. Note that DeepSeek-V4-Flash-0731 is a July 31 build, a version more than three months old.

vs Edge0-120B: the same-day sibling, with very little public data

Edge0-120B launched the same day as the 145B — the smaller tier of the same line. But as of Nov 20, 2026, neither the official blog nor the model cards publish the 120B's full specs or a six-benchmark comparison table. What this site's research confirms is only that it launched the same day, is likewise a latent-MoE derivative of Qwen3.8-Flash-Next, and likewise ships in Q3_K and NVFP4 builds. With no official 120B benchmark numbers, this site makes no quantified claim about "how much stronger the 145B is than the 120B"; which tier to pick awaits official 120B specs and scores, or independent testing. One warning: some third-party pieces quote Terminal-Bench figures for the 120B, but the numbers contradict each other across sources (75.3 vs 81.3) — none of them is used until officially confirmed.

Who should pick what: three users, three answers

Local agent and coding users: pick Edge0-145B. Its two leads (DeepSWE, Terminal-Bench) land exactly on your workload, and it is the only one of the three that runs locally — the base and DeepSeek-V4-Flash have no equivalent on-device form.

Knowledge Q&A and instruction-following first: the base may not be worse. The base leads on all three of HLE, GPQA-Diamond and IFBench; if your work runs in the cloud with no local-deployment need, there is no reason to switch models for a +1.1 mean.

On a budget and curious about on-device 145B: look at the 120B first. Until official 120B data is published, the value-for-money calculation cannot be done; decide big or small after the official figures or independent tests arrive.

ModelBrief's take: Rebuilding the MoE was a directional operation, not a general upgrade: big leads on coding and agents, small losses on knowledge and instruction-following, a mean gain of just 1.1 points. That shape is itself the conclusion — Edge0-145B is not "a general model better than its base" but "a base derivative specialized for local coding agents". The DeepSeek comparison says the same. The 120B sibling has no quotable official numbers yet, so no comparison is made.