DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
Official Hugging Face repo: Qwen/Qwen2.5-7B-Instruct.
12,229,058 downloads and 1,548 likes on the Hub API as of 2026-08-19.
Parameter count on the Hub card: 7.61B.
Context on the Hub card: 32,768 tokens.
Not present as a base OpenRouter slug in the 2026-08-19 catalog snapshot.
When you want the official Qwen/Qwen2.5-7B-Instruct checkpoint, not an Unsloth GGUF re-upload.
When the job is local text generation from the Hub weights.
No independent board lists this exact SKU as of 2026-08-19.
Closest benchmarked sibling: Qwen3.8 Max, 57% ±3% Pass@1 at xhigh on the DeepSWE official board. That is a score for the sibling, not for this SKU.
Boards checked: DeepSWE official (2026-08-13), Artificial Analysis Intelligence Index, vals.ai hero index. Every card that does carry a row is on the coding leaderboard.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
No Intelligence Index integer fetched for this identity. Chip omitted.
We did not open a vals.ai card for this identity. Chip omitted.
Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.
Official org repo. Community GGUF belongs as a quant link, not a second Continuum card.
This is the model repo, not Download for Mac. Downloads and likes from the Hugging Face API on 2026-08-19.
usedStorage and the sum of .safetensors sizes can differ (LFS pointers, non-shard files, duplicate copies). Cited separately. Source: recursive tree API, 2026-08-19.
| Path | Bytes |
|---|---|
model-00001-of-00004.safetensors | 3,945,441,440 |
model-00002-of-00004.safetensors | 3,864,726,352 |
model-00003-of-00004.safetensors | 3,864,726,424 |
model-00004-of-00004.safetensors | 3,556,377,672 |
tokenizer.json | 7,031,645 |
vocab.json | 2,776,833 |
merges.txt | 1,671,839 |
model.safetensors.index.json | 27,752 |
LICENSE | 11,343 |
tokenizer_config.json | 7,305 |
README.md | 6,240 |
.gitattributes | 1,519 |
config.json | 663 |
generation_config.json | 243 |
All 14 files the tree API returned are listed: every one of the 4 safetensor shards plus 10 other files. Files tab: https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/tree/main.
Hugging Face: Qwen/Qwen2.5-7B-Instruct.
Not on the 2026-08-19 OpenRouter catalog.
We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.
No OpenRouter price: this SKU was Hugging Face-only on 2026-08-19.
Hub-card context: 32,768 tokens.
| Claim | Source | As of |
|---|---|---|
| HF Qwen/Qwen2.5-7B-Instruct; downloads 12,229,058; likes 1,548 | Hugging Face API Qwen/Qwen2.5-7B-Instruct | 2026-08-19 |
| No base OpenRouter slug on the 2026-08-19 catalog; Hugging Face Qwen/Qwen2.5-7B-Instruct | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 12,229,058 | Hugging Face API Qwen/Qwen2.5-7B-Instruct | 2026-08-19 |
| HF safetensors.total: 7,615,616,512 stored tensors; HF API usedStorage 15,231,271,888 bytes; created 2024-09-16T11:55:40.000Z; HF tensors BF16 | Hugging Face API Qwen/Qwen2.5-7B-Instruct | 2026-08-19 |
| 4 safetensor shards; shard bytes 15,231,271,888; tree files 14 | Hugging Face tree API Qwen/Qwen2.5-7B-Instruct | 2026-08-19 |
No other card in this cluster shares a published DeepSWE official row we can put next to this one. We will not compare on vendor-blog numbers.
Continue through Qwen's model family with Qwen3.8 Max.
Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.
No Continuum hosted id is verified for this model, so this page does not invent a curl target. This SKU was Hugging Face-only on the 2026-08-19 OpenRouter catalog.