Views
No views yet
Qwen's AgentWorld 35B-total / 3B-active hybrid MoE (linear-attention + sparse experts), quantized to a ~11.6 GB IQ2_M that runs on a 16 GB machine and autonomously solves real SWE-bench Verified bugs. This is Qwen's model — ours is the quant (imatrix) + the eval + the configurable-context Modelfiles. No GGUF existed yet; this is the first.
qwen35moe, a hybrid that mixes linear-attention (gated delta-net + conv) layers with full-attention layers, on top of a 256-expert MoE (8 active). It needs a recent llama.cpp / Ollama with qwen35moe runtime support — older builds (and Ollama ≤ 0.20.x at time of writing) cannot run it. Build llama.cpp from master.| file | bits | size | pick this if… |
|---|---|---|---|
AgentWorld-35B-A3B-IQ2_M.gguf | ~2.7 | ~11.6 GB | the one in this repo — smallest that's still sharp (imatrix-guided). Runs in ~13–16 GB. |
| you have | context you can run |
|---|---|
| 16 GB | ~8–32K |
| 24 GB | ~64–128K |
| 32 GB+ | up to native 256K |
CONTEXT.md.1# Build a recent llama.cpp first (master has qwen35moe support):
2# git clone https://github.com/ggml-org/llama.cpp && cmake -B build -DGGML_METAL=ON && cmake --build build -j
3
4# llama.cpp (OpenAI-compatible server, native tool-calls via --jinja):
5llama-server -m AgentWorld-35B-A3B-IQ2_M.gguf -c 32768 --jinja -ngl 99
6
7# Ollama (recent build that supports qwen35moe):
8ollama create agentworld-32k -f Modelfile.32768 && ollama run agentworld-32k<think> reasoning channel; --jinja parses it into reasoning_content and tool calls into native tool_calls.--jinja (no <function=>/text-injection workaround needed). In a Claude-Code-style harness it also reliably emits raw-JSON {"name":…, "arguments":…} tool calls.max_tokens ~8K to bound it). It's a world-model/agent model (the upstream is multimodal; this GGUF is text-only — vision is not converted).swe-mix anchor smoke (see below). The confirmed real solve: django__django-11099 (is_resolved: True, 1/1 tests, 37 tool calls, autonomous). django__django-11133 attempted but not resolved (0/1); astropy__astropy-14369 (a "1-4 hour" hard task) timed out under the 25-min watchdog. (A full 30-instance swe-mix run was not completed for this first-mover release; this is an honest agentic smoke, not the full probe.)django__django-11099 (resolved), django__django-11133 (0/1), astropy__astropy-14369 (timeout) — anchors from the swe-mix probe (full 30-instance spec in swe_mix.json: 6 continuity anchors + 24 discriminating, 10 repos, SWE-bench Verified).llama-server (master build, Metal) on an OpenAI /v1 endpoint.tool_calls (via --jinja) → bridge raw-JSON.--allow-requantize).