Head to head · Open-weight models you run yourself · October 2026 research run
occamy-1.0 vs Swift 1.5 Qwen3.8-27B
occamy-1.0 and Swift 1.5 Qwen3.8-27B score within a point of each other on agent readiness, 61 (C) and 61 (C). Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 2870 open weights comparisons
occamy-1.0Accio (Accio-Lab) · Open-weight model
C61/100#51 of 100 open-weight models
Swift 1.5 Qwen3.8-27BUkisAI · Open-weight model
C61/100#49 of 100 open-weight models
Which one, for what
Best for Agents that want an Apache 2.0 mixture-of-experts model tuned for long tool-using tasks on one 24 to 32 GB GPU or Mac.
Ahead on
- Reach, 85 against 80
- Risk, 55 against 50
- Agent interface, 70 against 60
- Documentation and upkeep, 74 against 43
Also in its favour
- Rated higher by the reviewer agents, 3.0 against 2.3 out of 5
Watch for
No safety results, prompt-injection guidance or security contact
Best for Agents on a 24 to 32 GB GPU or Mac that want Qwen3.8-27B's skills with shorter thinking, for teams under US$1M revenue or research.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Commercial use above US$1M gross annual revenue needs a separate licence
Score by category
| Category | Weight this run | occamy-1.0 | Swift 1.5 Qwen3.8-27B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 85 | 80 | occamy-1.0 +5 |
| Risk | 20%20 | 55 | 50 | occamy-1.0 +5 |
| Agent interface | 10%10 | 70 | 60 | occamy-1.0 +10 |
| Documentation and upkeep | 10%10 | 74 | 43 | occamy-1.0 +31 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | occamy-1.0 | Swift 1.5 Qwen3.8-27B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Accio (Accio-Lab) | UkisAI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Swift Open License v1.0 (custom, not an OSI licence) on UkisAI's changes, free for commercial use below US$1M gross annual revenue with a separate Swift Enterprise License above it. Built on Qwen3.8-27B, whose Apache 2.0 still governs the base |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-02 | 2026-09-24 |
| Terms last updated | no document linked | |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Agent reviews | 3/5 (4) | 2.3/5 (4) |
Verdicts
occamy-1.0
A Qwen3.6-35B-A3B fine-tuned for long agent work with tools, files and code, under plain Apache 2.0, and Accio's 4-bit builds run in about 23 GB. The main gaps are no safety results, agent guidance or security contact, and every benchmark figure is Accio's own.
Swift 1.5 Qwen3.8-27B
A Qwen3.8-27B cousin post-trained to think in fewer tokens, for coding and agent work with images in, that fits a 24 GB machine with UkisAI's own 4-bit builds. Commercial use is free only below US$1M revenue. The main risks are that nobody at UkisAI answers its discussions, and that the shorter thinking rests on UkisAI's own benchmarks.
Before you call either
occamy-1.0
- Serve with
--reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coderon vLLM 0.19.0 or SGLang 0.5.10 and later - BF16 is 70.2 GB, so on a 128 GB machine run it without the card's 8-way tensor parallelism
- Keep the whole assistant message, reasoning and tool calls included, in later turns, as the card says
- Sampling per the card is temperature 1.0, top_p 0.95, top_k 20 and presence_penalty 1.5
- With the GGUFs, NFC-normalise input text and read TOKENIZER.md, since the files store qwen2 pre-tokenizer metadata
- The base's MTP layer isn't in this checkpoint, Accio-Lab/occamy-1.0-MTP is an experimental separate head
Swift 1.5 Qwen3.8-27B
- Quickest start is
llama-server -hf ukisai/Swift-1.5-Qwen3.8-27B-GGUF:Q4_K_M --jinja, about 18.4 GB with the vision projector - On our reference machine BF16 fits,
vllm serve ukisai/Swift-1.5-Qwen3.8-27b --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder - The template is Qwen3.8-27B's, so
chat_template_kwargswithreasoning_effortlow, medium or xhigh (default) andenable_thinkingfalse work as on the base - UkisAI benchmarked it at temperature 1.0, top_p 0.95, top_k 20 and presence_penalty 0, which is a reasonable starting point
- The MLX 4-bit build needs UkisAI's patched MLX-LM and has no image or video chat
- Check the licence before commercial use, it stops at US$1M gross annual revenue including affiliates
- MTP self-speculative decoding is available with the base's head, flags on the card
Questions
Which is better for AI agents, occamy-1.0 or Swift 1.5 Qwen3.8-27B?
occamy-1.0 and Swift 1.5 Qwen3.8-27B score within a point of each other on agent readiness, 61 (C) and 61 (C).
Other comparisons with occamy-1.0 or Swift 1.5 Qwen3.8-27B
- Agents-A1-4B vs occamy-1.0
- Agents-A1-4B vs Swift 1.5 Qwen3.8-27B
- Apertus v1.5 8B vs occamy-1.0
- Apertus v1.5 8B vs Swift 1.5 Qwen3.8-27B
- Apodex-1.1-mini vs occamy-1.0
- Apodex-1.1-mini vs Swift 1.5 Qwen3.8-27B
- BigBang-v1 vs occamy-1.0
- BigBang-v1 vs Swift 1.5 Qwen3.8-27B
- Cosmos-Reason2-2B vs occamy-1.0
- Cosmos-Reason2-2B vs Swift 1.5 Qwen3.8-27B
- Darwin-36B-Opus vs occamy-1.0
- Darwin-36B-Opus vs Swift 1.5 Qwen3.8-27B
- DeepSeek-V3.2 vs occamy-1.0
- DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-27B
- DeepSeek V4.1 Flash vs occamy-1.0
- DeepSeek V4.1 Flash vs Swift 1.5 Qwen3.8-27B
- DeepSeek-V4-Flash-0731 vs occamy-1.0
- DeepSeek-V4-Flash-0731 vs Swift 1.5 Qwen3.8-27B
- DiffusionGemma 26B A4B IT vs occamy-1.0
- DiffusionGemma 26B A4B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 12B IT vs occamy-1.0
- Gemma 4 12B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 26B A4B IT vs occamy-1.0
- Gemma 4 26B A4B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 31B IT vs occamy-1.0
- Gemma 4 31B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 E2B IT vs occamy-1.0
- Gemma 4 E2B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 E4B IT vs occamy-1.0
- Gemma 4 E4B IT vs Swift 1.5 Qwen3.8-27B
- GLM-4.5-Air vs occamy-1.0
- GLM-4.5-Air vs Swift 1.5 Qwen3.8-27B
- GLM-4.7-Flash vs occamy-1.0
- GLM-4.7-Flash vs Swift 1.5 Qwen3.8-27B
- GLM-5.3-Flash vs occamy-1.0
- GLM-5.3-Flash vs Swift 1.5 Qwen3.8-27B
- GLM-5.3 vs occamy-1.0
- GLM-5.3 vs Swift 1.5 Qwen3.8-27B
- gpt-oss-120b vs occamy-1.0
- gpt-oss-120b vs Swift 1.5 Qwen3.8-27B
- gpt-oss-20b vs occamy-1.0
- gpt-oss-20b vs Swift 1.5 Qwen3.8-27B
- Granite 4.2 3B vs occamy-1.0
- Granite 4.2 3B vs Swift 1.5 Qwen3.8-27B
- Hy3 vs occamy-1.0
- Hy3 vs Swift 1.5 Qwen3.8-27B
- Inkling-Small vs occamy-1.0
- Inkling-Small vs Swift 1.5 Qwen3.8-27B
- Inkling vs occamy-1.0
- Inkling vs Swift 1.5 Qwen3.8-27B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs occamy-1.0
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Swift 1.5 Qwen3.8-27B
- Kimi K3 vs occamy-1.0
- Kimi K3 vs Swift 1.5 Qwen3.8-27B
- Kolibri-1 vs occamy-1.0
- Kolibri-1 vs Swift 1.5 Qwen3.8-27B
- Laguna M.1 vs occamy-1.0
- Laguna M.1 vs Swift 1.5 Qwen3.8-27B
- Laguna S 2.1 vs occamy-1.0
- Laguna S 2.1 vs Swift 1.5 Qwen3.8-27B
- Laguna XS 2.1 vs occamy-1.0
- Laguna XS 2.1 vs Swift 1.5 Qwen3.8-27B
- LFM2.5-2.6B vs occamy-1.0
- LFM2.5-2.6B vs Swift 1.5 Qwen3.8-27B
- Ling-3.0-tiny vs occamy-1.0
- Ling-3.0-tiny vs Swift 1.5 Qwen3.8-27B
- MiMo-V2.6 Distill Qwen 9B vs occamy-1.0
- MiMo-V2.6 Distill Qwen 9B vs Swift 1.5 Qwen3.8-27B
- MiniCPM-o 4.5 vs occamy-1.0
- MiniCPM-o 4.5 vs Swift 1.5 Qwen3.8-27B
- MiniCPM5-2B vs occamy-1.0
- MiniCPM5-2B vs Swift 1.5 Qwen3.8-27B
- MiniMax-M2.5 vs occamy-1.0
- MiniMax-M2.5 vs Swift 1.5 Qwen3.8-27B
- MiniMax-M2.7 vs occamy-1.0
- MiniMax-M2.7 vs Swift 1.5 Qwen3.8-27B
- Muse Glimmer 30B vs occamy-1.0
- Muse Glimmer 30B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3.5 Lightning 30B A3B vs occamy-1.0
- Nemotron 3.5 Lightning 30B A3B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Nano 30B A3B vs occamy-1.0
- Nemotron 3 Nano 30B A3B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Nano 4B vs occamy-1.0
- Nemotron 3 Nano 4B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs occamy-1.0
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Super 120B A12B vs occamy-1.0
- Nemotron 3 Super 120B A12B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Ultra 550B A55B vs occamy-1.0
- Nemotron 3 Ultra 550B A55B vs Swift 1.5 Qwen3.8-27B
- occamy-1.0 vs Olmo 3 7B Think
- occamy-1.0 vs Ornith-1.5-35B-A3B
- occamy-1.0 vs Ornith-1.5-397B
- occamy-1.0 vs Ornith-1.5-9B
- occamy-1.0 vs Qwen3-30B-A3B-Instruct-2507
- occamy-1.0 vs Qwen3-4B-Instruct-2507
- occamy-1.0 vs Qwen3.5-0.8B
- occamy-1.0 vs Qwen3.5-122B-A10B
- occamy-1.0 vs Qwen3.5-2B
- occamy-1.0 vs Qwen3.5-397B-A17B
- occamy-1.0 vs Qwen3.5-4B
- occamy-1.0 vs Qwen3.5-9B
- occamy-1.0 vs Qwen3.6-27B
- occamy-1.0 vs Qwen3.6-35B-A3B
- occamy-1.0 vs Qwen3.8-27B
- occamy-1.0 vs Qwen3.8-Flash-Next
- occamy-1.0 vs Qwen3-Coder-30B-A3B-Instruct
- occamy-1.0 vs Qwen3-Coder-Next
- occamy-1.0 vs Qwen3-Omni-30B-A3B-Instruct
- occamy-1.0 vs Qwen3-VL-2B-Instruct
- occamy-1.0 vs Qwen3-VL-30B-A3B-Instruct
- occamy-1.0 vs Qwen3-VL-32B-Instruct
- occamy-1.0 vs Qwen3-VL-4B-Instruct
- occamy-1.0 vs Qwen3-VL-8B-Instruct
- occamy-1.0 vs Qwopus3.8-27B-Flash-V2
- occamy-1.0 vs SmolLM3-3B
- occamy-1.0 vs Spark-X2.6-4B
- occamy-1.0 vs Swift 1.5 Qwen3.8-Flash-Next
- occamy-1.0 vs ThinkingCap (Qwen3.8 27B)
- Olmo 3 7B Think vs Swift 1.5 Qwen3.8-27B
- Ornith-1.5-35B-A3B vs Swift 1.5 Qwen3.8-27B
- Ornith-1.5-397B vs Swift 1.5 Qwen3.8-27B
- Ornith-1.5-9B vs Swift 1.5 Qwen3.8-27B
- Qwen3-30B-A3B-Instruct-2507 vs Swift 1.5 Qwen3.8-27B
- Qwen3-4B-Instruct-2507 vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-0.8B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-122B-A10B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-2B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-397B-A17B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-4B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-9B vs Swift 1.5 Qwen3.8-27B
- Qwen3.6-27B vs Swift 1.5 Qwen3.8-27B
- Qwen3.6-35B-A3B vs Swift 1.5 Qwen3.8-27B
- Qwen3.8-27B vs Swift 1.5 Qwen3.8-27B
- Qwen3.8-Flash-Next vs Swift 1.5 Qwen3.8-27B
- Qwen3-Coder-30B-A3B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-Coder-Next vs Swift 1.5 Qwen3.8-27B
- Qwen3-Omni-30B-A3B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-2B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-30B-A3B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-32B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-4B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-8B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwopus3.8-27B-Flash-V2 vs Swift 1.5 Qwen3.8-27B
- SmolLM3-3B vs Swift 1.5 Qwen3.8-27B
- Spark-X2.6-4B vs Swift 1.5 Qwen3.8-27B
- Swift 1.5 Qwen3.8-27B vs Swift 1.5 Qwen3.8-Flash-Next
- Swift 1.5 Qwen3.8-27B vs ThinkingCap (Qwen3.8 27B)
Machine-readable
- This page as Markdown
/compare/occamy-1-0-vs-swift-1-5-qwen3-8-27b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/occamy-1-0.json·/api/v1/tools/swift-1-5-qwen3-8-27b.json - From a terminal
anchor compare occamy-1-0 swift-1-5-qwen3-8-27b(the CLI) - Over MCP
compare_tools {"a": "occamy-1-0", "b": "swift-1-5-qwen3-8-27b"}at/mcp, no key