Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 8B vs Qwen3.5-9B
Granite 4.2 8B and Qwen3.5-9B score within a point of each other on agent readiness, 61 (C) and 60.5 (C). Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 4969 open weights comparisons
Which one, for what
Best for Agents that want a documented, signed, Apache 2.0 reasoning model with tool calling on a 16 GB machine
Ahead on
- Reach, 95 against 85
- Agent interface, 85 against 70
- Documentation and upkeep, 92 against 34
Watch for
No safety results published for it
Best for Agents that want a small multimodal tool-calling model on a laptop or a 16 GB GPU, under a plain licence
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No quantised build from Qwen itself
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Documentation and upkeep Granite 4.2 8B +58
Granite 4.2 8B 92
Model card 17, Intended use (best for), limitations (ethical considerations and limitations), architecture, parameters (8B), context length (128K native) and 12 tested languages are on the card. Training data 20, IBM's disclosure file for the 8B lists the datasets used in pre-training and post-training as machine-readable metadata, and the card describes the three training stages. Last change 20, the last commit, on 20 October 2026, replaced model.safetensors.index.json (titled "granite-4.2 index file fix"), 21 days before this check. Responsiveness 20, Of the 5 discussions that aren't pull requests (13 September to 5 November 2026), 4 have a reply from an ibm-granite member. Version policy 5, Granite 4.1 8B stays in its own repository and 4.2 came out in new ones. File health 10, Config, template and card agree on the architecture, the 131,072-token context and the thinking switch. 17 + 20 + 20 + 20 + 5 + 10 = 92.
Qwen3.5-9B 34
Model card 14, it covers intended use, architecture, parameters, context and 201 languages but gives no limitations and no knowledge cut-off. Training data 5, a general line about trillions of multimodal tokens with no cut-off. Last change 5, the files and card last changed on 2 March 2026 (c202236), 247 days before 4 November, within a year. Responsiveness 0, no Qwen member replied in any of the 40 most recent of the 45 discussions that aren't pull requests (2 March to 29 September 2026). Version policy 5, a first release that was never replaced in place, with no dated notes across generations. File health 5, two reports about the files and card (15 and 51) are still open with no reply. 14 + 5 + 5 + 0 + 5 + 5 = 34. The card's highlights mention sparse Mixture-of-Experts for the series while this 9B is dense, but its own overview matches config.json, so it's not counted as a contradiction.
Agent interface Granite 4.2 8B +15
Granite 4.2 8B 85
Chat template 20, chat_template.jinja in the repository, with roles, tools, tool responses, the thinking switch and low effort. Tool-calling format 25, the card has tool-calling sections for vLLM and SGLang, declares tools with OpenAI's function schema and names the parser to use, qwen3_coder, which both runtimes ship in the released versions read. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so it renders several calls in one turn, and the card names tool calling and agentic workflows as what it's best for. Structured output 0, the card doesn't document JSON or JSON Schema output or how to ask for it. Reasoning control 10, the card documents thinking on by default, non-thinking and low-effort modes per request through the template (enable_thinking and low_effort), with the reasoning returned apart from the answer. Context 10, 131,072 tokens natively per the card and config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.
Qwen3.5-9B 70
Chat template 20, a Jinja file in the repository. Tool-calling format 10, the card names the qwen3_coder parser for vLLM and SGLang but leaves the declaration and return format to the template, and Qwen's own function-calling guide still describes Qwen3's Hermes format. Trained tool calling 20, the template renders several calls in one turn. Structured output 0, nothing documents asking the weights for JSON. Reasoning control 10, thinking turns off per request with enable_thinking false and the reasoning comes back in think tags that the qwen3 parser splits out. Context 10, 262,144 tokens native.
Reach Granite 4.2 8B +10
Granite 4.2 8B 95
Memory 30, IBM's own 4-bit MLX build granite-4.2-8b-q4-mlx is 4.95 GB, and 4.95 GB × 1.2 = 5.9 GB, within 8 GB. Its Q4_0 GGUF is 5.06 GB and Ollama's library build granite4.2:8b (5.3 GB) fits 8 GB too. Runtimes 25, Released versions run the granite architecture in llama.cpp (granite, b12242), vLLM (GraniteForCausalLM in the v0.33.0 registry), SGLang (granite.py at v0.5.23), Transformers (v5.22.2) and Ollama (its own granite4.2 library entry, 8b tag). Builds 15, IBM publishes FP8, MXFP4 and NVFP4 safetensors builds, a GGUF repository with Q4_0 to Q8_0 and BF16 files, and 4-bit, 8-bit and BF16 MLX builds, so quantised builds at two precisions or more. Terms 15, Apache 2.0, an OSI-approved licence, with no use policy or other terms added on the card. Download 10, the Hub API reports gated false for the BF16, FP8, MXFP4, NVFP4, GGUF and MLX repositories, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps one inference provider (DeepInfra, live), short of the two the line needs. 30 + 25 + 15 + 15 + 10 + 0 = 95.
Qwen3.5-9B 85
Memory 30, Qwen publishes no quantised 9B, so the smallest 4-bit build from a runtime's own library is Ollama's qwen3.5:9b at 6.6 GB, about 7.9 GB with the fifth added, well under 16 GB. Runtimes 25, the cap, with vLLM listed in its stable docs, Transformers at released tags, llama.cpp, Ollama's library, LM Studio's own catalogue and SGLang all running the architecture. Builds 0, Qwen's FP8 and GPTQ repositories cover only the 27B and larger Qwen3.5 models, so every quantisation of the 9B is someone else's. Terms 15, plain Apache 2.0. Download 10, the repository isn't gated. Hosted 5, Together, Featherless AI, OVHcloud and DeepInfra are live for it on its Hugging Face page. 30 + 25 + 0 + 15 + 10 + 5 = 85.
Score by category
| Category | Weight this run | Granite 4.2 8B | Qwen3.5-9B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 95 | 85 | Granite 4.2 8B +10 |
| Risk | 20%20 | 55 | 55 | even |
| Agent interface | 10%10 | 85 | 70 | Granite 4.2 8B +15 |
| Documentation and upkeep | 10%10 | 92 | 34 | Granite 4.2 8B +58 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 60.5/100 |
Facts side by side
| Fact | Granite 4.2 8B | Qwen3.5-9B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | IBM | Alibaba (Qwen team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-20 | 2026-03-02 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | none | 2.5/5 (4) |
Verdicts
Granite 4.2 8B
IBM's mid-size reasoning cousin, with the same strengths as the 3B. It runs in every runtime we count from IBM's own builds on a 16 GB machine, is signed, plain Apache 2.0, and comes with a disclosure of its training data. No safety results are published and structured output isn't documented.
Qwen3.5-9B
A small dense vision-language model with trained tool calling, thinking that turns off per request and a 262,144-token context. Ollama's 4-bit build is 6.6 GB and the BF16 files 19.3 GB, and every major runtime loads it. The files haven't changed since 2 March 2026, Qwen answered none of the 40 latest discussions, and no safety results are published.
Before you call either
Granite 4.2 8B
- Start it with
ollama run granite4.2:8b, orllama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q4_K_M --jinja - With vLLM 0.32.0 or later leave out
--reasoning-parser-plugin, since the parser is built in, and use--tool-call-parser qwen3_coder - Thinking is on by default. Pass
enable_thinkingfalse to turn it off orlow_efforttrue for short reasoning - The context is 131,072 tokens. The card's 512K extension isn't documented
- Validate JSON output yourself, since structured output isn't documented
- IBM recommends Granite Guardian beside it to flag risky inputs and outputs
Qwen3.5-9B
- Smallest start is
ollama run qwen3.5:9b(6.6 GB, q4_k_m) - On vLLM run
vllm serve Qwen/Qwen3.5-9B --port 8000 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder, or tool calls come back as text - Tool calls use the XML style
<tool_call><function=name><parameter=x>, not Hermes JSON, so use the qwen3_coder parser and not hermes - Thinking is on by default; pass
chat_template_kwargswithenable_thinkingfalse for short tasks, since/nothinkisn't supported - There's no generation_config.json, so pass sampling yourself, temperature 1.0, top_p 0.95, top_k 20, presence_penalty 1.5 when thinking, or 0.7, 0.8, 20, 1.5 without
- Keep at least 128K of context when thinking, and turn on YaRN only beyond 262,144 tokens
- Validate JSON output yourself or use the runtime's guided decoding
Questions
Which is better for AI agents, Granite 4.2 8B or Qwen3.5-9B?
Granite 4.2 8B and Qwen3.5-9B score within a point of each other on agent readiness, 61 (C) and 60.5 (C).
Other comparisons with Granite 4.2 8B or Qwen3.5-9B
- Agents-A1-4B vs Granite 4.2 8B
- Agents-A1-4B vs Qwen3.5-9B
- Apertus v1.5 8B vs Granite 4.2 8B
- Apertus v1.5 8B vs Qwen3.5-9B
- Apodex-1.1-mini vs Granite 4.2 8B
- Apodex-1.1-mini vs Qwen3.5-9B
- Arete-27B vs Granite 4.2 8B
- Arete-27B vs Qwen3.5-9B
- BigBang-v1 vs Granite 4.2 8B
- BigBang-v1 vs Qwen3.5-9B
- Carbon-X vs Granite 4.2 8B
- Carbon-X vs Qwen3.5-9B
- Cosmos-Reason2-2B vs Granite 4.2 8B
- Cosmos-Reason2-2B vs Qwen3.5-9B
- Darwin-36B-Opus vs Granite 4.2 8B
- Darwin-36B-Opus vs Qwen3.5-9B
- DeepSeek-V3.2 vs Granite 4.2 8B
- DeepSeek-V3.2 vs Qwen3.5-9B
- DeepSeek V4.1 Flash vs Granite 4.2 8B
- DeepSeek V4.1 Flash vs Qwen3.5-9B
- DeepSeek-V4-Flash-0731 vs Granite 4.2 8B
- DeepSeek-V4-Flash-0731 vs Qwen3.5-9B
- DiffusionGemma 26B A4B IT vs Granite 4.2 8B
- DiffusionGemma 26B A4B IT vs Qwen3.5-9B
- Gemma 4 12B IT vs Granite 4.2 8B
- Gemma 4 12B IT vs Qwen3.5-9B
- Gemma 4 26B A4B IT vs Granite 4.2 8B
- Gemma 4 26B A4B IT vs Qwen3.5-9B
- Gemma 4 31B IT vs Granite 4.2 8B
- Gemma 4 31B IT vs Qwen3.5-9B
- Gemma 4 E2B IT vs Granite 4.2 8B
- Gemma 4 E2B IT vs Qwen3.5-9B
- Gemma 4 E4B IT vs Granite 4.2 8B
- Gemma 4 E4B IT vs Qwen3.5-9B
- GLM-4.5-Air vs Granite 4.2 8B
- GLM-4.5-Air vs Qwen3.5-9B
- GLM-4.7-Flash vs Granite 4.2 8B
- GLM-4.7-Flash vs Qwen3.5-9B
- GLM-5.3-Flash vs Granite 4.2 8B
- GLM-5.3-Flash vs Qwen3.5-9B
- GLM-5.3 vs Granite 4.2 8B
- GLM-5.3 vs Qwen3.5-9B
- gpt-oss-120b vs Granite 4.2 8B
- gpt-oss-120b vs Qwen3.5-9B
- gpt-oss-20b vs Granite 4.2 8B
- gpt-oss-20b vs Qwen3.5-9B
- Granite 4.2 30B vs Granite 4.2 8B
- Granite 4.2 30B vs Qwen3.5-9B
- Granite 4.2 3B vs Granite 4.2 8B
- Granite 4.2 3B vs Qwen3.5-9B
- Granite 4.2 8B vs Hy-Memory-30B-A3B
- Granite 4.2 8B vs Hy3
- Granite 4.2 8B vs Inkling
- Granite 4.2 8B vs Inkling-Small
- Granite 4.2 8B vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Granite 4.2 8B vs Kimi K3
- Granite 4.2 8B vs Kimi K3.1 Pro
- Granite 4.2 8B vs Kolibri-1
- Granite 4.2 8B vs Kronos
- Granite 4.2 8B vs Laguna M.1
- Granite 4.2 8B vs Laguna S 2.1
- Granite 4.2 8B vs Laguna XS 2.1
- Granite 4.2 8B vs LBS-27B
- Granite 4.2 8B vs LFM2.5-2.6B
- Granite 4.2 8B vs LFM3-1.7B
- Granite 4.2 8B vs LFM3-Audio-2B
- Granite 4.2 8B vs LFM3-Omni-2B
- Granite 4.2 8B vs LFM3-VL-2B
- Granite 4.2 8B vs Ling-3.0-tiny
- Granite 4.2 8B vs Ling-3.1-flash-1019
- Granite 4.2 8B vs MiMo-V2.6 Distill Qwen 9B
- Granite 4.2 8B vs MiniCPM-o 4.5
- Granite 4.2 8B vs MiniCPM-V 4.7 1B
- Granite 4.2 8B vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 8B vs MiniCPM5-2B
- Granite 4.2 8B vs MiniMax-M2.5
- Granite 4.2 8B vs MiniMax-M2.7
- Granite 4.2 8B vs MiniMax-M3.1-Flash
- Granite 4.2 8B vs Mistral Large 4
- Granite 4.2 8B vs Muse Glimmer 30B
- Granite 4.2 8B vs Nanbeige4.3-33B
- Granite 4.2 8B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Granite 4.2 8B vs Nemotron 3.5 Lightning 30B A3B
- Granite 4.2 8B vs Nemotron 3 Nano 30B A3B
- Granite 4.2 8B vs Nemotron 3 Nano 4B
- Granite 4.2 8B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Granite 4.2 8B vs Nemotron 3 Super 120B A12B
- Granite 4.2 8B vs Nemotron 3 Ultra 550B A55B
- Granite 4.2 8B vs occamy-1.0
- Granite 4.2 8B vs Olmo 3 7B Think
- Granite 4.2 8B vs Ornith-1.5-122B
- Granite 4.2 8B vs Ornith-1.5-35B-A3B
- Granite 4.2 8B vs Ornith-1.5-397B
- Granite 4.2 8B vs Ornith-1.5-9B
- Granite 4.2 8B vs Qwen-AgentWorld-35B-A3B
- Granite 4.2 8B vs Qwen3-30B-A3B-Instruct-2507
- Granite 4.2 8B vs Qwen3-4B-Instruct-2507
- Granite 4.2 8B vs Qwen3.5-0.8B
- Granite 4.2 8B vs Qwen3.5-122B-A10B
- Granite 4.2 8B vs Qwen3.5-2B
- Granite 4.2 8B vs Qwen3.5-397B-A17B
- Granite 4.2 8B vs Qwen3.5-4B
- Granite 4.2 8B vs Qwen3.6-27B
- Granite 4.2 8B vs Qwen3.6-35B-A3B
- Granite 4.2 8B vs Qwen3.8-27B
- Granite 4.2 8B vs Qwen3.8-Flash-Next
- Granite 4.2 8B vs Qwen3-Coder-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-Coder-Next
- Granite 4.2 8B vs Qwen3-Omni-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-VL-2B-Instruct
- Granite 4.2 8B vs Qwen3-VL-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-VL-32B-Instruct
- Granite 4.2 8B vs Qwen3-VL-4B-Instruct
- Granite 4.2 8B vs Qwen3-VL-8B-Instruct
- Granite 4.2 8B vs Qwopus3.8-27B-Flash-V2
- Granite 4.2 8B vs Recursive Flint
- Granite 4.2 8B vs Ripple-65B Preview
- Granite 4.2 8B vs SmolLM3-3B
- Granite 4.2 8B vs Spark-X2.6-4B
- Granite 4.2 8B vs Swift 1.5 Qwen3.8-27B
- Granite 4.2 8B vs Swift 1.5 Qwen3.8-Flash-Next
- Granite 4.2 8B vs ThinkingCap (Qwen3.8 27B)
- Granite 4.2 8B vs Baidu Unlimited-OCR-2
- Hy-Memory-30B-A3B vs Qwen3.5-9B
- Hy3 vs Qwen3.5-9B
- Inkling-Small vs Qwen3.5-9B
- Inkling vs Qwen3.5-9B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.5-9B
- Kimi K3.1 Pro vs Qwen3.5-9B
- Kimi K3 vs Qwen3.5-9B
- Kolibri-1 vs Qwen3.5-9B
- Kronos vs Qwen3.5-9B
- Laguna M.1 vs Qwen3.5-9B
- Laguna S 2.1 vs Qwen3.5-9B
- Laguna XS 2.1 vs Qwen3.5-9B
- LBS-27B vs Qwen3.5-9B
- LFM2.5-2.6B vs Qwen3.5-9B
- LFM3-1.7B vs Qwen3.5-9B
- LFM3-Audio-2B vs Qwen3.5-9B
- LFM3-Omni-2B vs Qwen3.5-9B
- LFM3-VL-2B vs Qwen3.5-9B
- Ling-3.0-tiny vs Qwen3.5-9B
- Ling-3.1-flash-1019 vs Qwen3.5-9B
- MiMo-V2.6 Distill Qwen 9B vs Qwen3.5-9B
- MiniCPM-o 4.5 vs Qwen3.5-9B
- MiniCPM-V 4.7 1B vs Qwen3.5-9B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5-9B
- MiniCPM5-2B vs Qwen3.5-9B
- MiniMax-M2.5 vs Qwen3.5-9B
- MiniMax-M2.7 vs Qwen3.5-9B
- MiniMax-M3.1-Flash vs Qwen3.5-9B
- Mistral Large 4 vs Qwen3.5-9B
- Muse Glimmer 30B vs Qwen3.5-9B
- Nanbeige4.3-33B vs Qwen3.5-9B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Qwen3.5-9B
- Nemotron 3.5 Lightning 30B A3B vs Qwen3.5-9B
- Nemotron 3 Nano 30B A3B vs Qwen3.5-9B
- Nemotron 3 Nano 4B vs Qwen3.5-9B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Qwen3.5-9B
- Nemotron 3 Super 120B A12B vs Qwen3.5-9B
- Nemotron 3 Ultra 550B A55B vs Qwen3.5-9B
- occamy-1.0 vs Qwen3.5-9B
- Olmo 3 7B Think vs Qwen3.5-9B
- Ornith-1.5-122B vs Qwen3.5-9B
- Ornith-1.5-35B-A3B vs Qwen3.5-9B
- Ornith-1.5-397B vs Qwen3.5-9B
- Ornith-1.5-9B vs Qwen3.5-9B
- Qwen-AgentWorld-35B-A3B vs Qwen3.5-9B
- Qwen3-30B-A3B-Instruct-2507 vs Qwen3.5-9B
- Qwen3-4B-Instruct-2507 vs Qwen3.5-9B
- Qwen3.5-0.8B vs Qwen3.5-9B
- Qwen3.5-122B-A10B vs Qwen3.5-9B
- Qwen3.5-2B vs Qwen3.5-9B
- Qwen3.5-397B-A17B vs Qwen3.5-9B
- Qwen3.5-4B vs Qwen3.5-9B
- Qwen3.5-9B vs Qwen3.6-27B
- Qwen3.5-9B vs Qwen3.6-35B-A3B
- Qwen3.5-9B vs Qwen3.8-27B
- Qwen3.5-9B vs Qwen3.8-Flash-Next
- Qwen3.5-9B vs Qwen3-Coder-30B-A3B-Instruct
- Qwen3.5-9B vs Qwen3-Coder-Next
- Qwen3.5-9B vs Qwen3-Omni-30B-A3B-Instruct
- Qwen3.5-9B vs Qwen3-VL-2B-Instruct
- Qwen3.5-9B vs Qwen3-VL-30B-A3B-Instruct
- Qwen3.5-9B vs Qwen3-VL-32B-Instruct
- Qwen3.5-9B vs Qwen3-VL-4B-Instruct
- Qwen3.5-9B vs Qwen3-VL-8B-Instruct
- Qwen3.5-9B vs Qwopus3.8-27B-Flash-V2
- Qwen3.5-9B vs Recursive Flint
- Qwen3.5-9B vs Ripple-65B Preview
- Qwen3.5-9B vs SmolLM3-3B
- Qwen3.5-9B vs Spark-X2.6-4B
- Qwen3.5-9B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-9B vs Swift 1.5 Qwen3.8-Flash-Next
- Qwen3.5-9B vs ThinkingCap (Qwen3.8 27B)
- Qwen3.5-9B vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/granite-4-2-8b-vs-qwen3-5-9b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/granite-4-2-8b.json·/api/v1/tools/qwen3-5-9b.json - From a terminal
anchor compare granite-4-2-8b qwen3-5-9b(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-8b", "b": "qwen3-5-9b"}at/mcp, no key