Downloads · 30 days
33
6% of all-time downloads
KikoCis/Qwen-AgentWorld-35B-A3B-IQ2_M-GGUF
Qwen-AgentWorld-35B-A3B-IQ2_M-GGUF is a machine learning model from KikoCis. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Downloads · 30 days
33
6% of all-time downloads
All-time downloads
526
Public
Repo size
11.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf11.7 GB · 98%
From the Hugging Face model README

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.
Heads-up — brand-new architecture: AgentWorld is 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. |
Total memory ≈ ~11.6 GB weights + KV-cache (grows with context). Only 3B params are active per token, so it's fast for its size.
| you have | context you can run |
|---|---|
| 16 GB | ~8–32K |
| 24 GB | ~64–128K |
| 32 GB+ | up to native 256K |
Configurable — Modelfiles at 8K / 32K / 128K / native are included; see CONTEXT.md.
# Build a recent llama.cpp first (master has qwen35moe support):
# git clone https://github.com/ggml-org/llama.cpp && cmake -B build -DGGML_METAL=ON && cmake --build build -j
# llama.cpp (OpenAI-compatible server, native tool-calls via --jinja):
llama-server -m AgentWorld-35B-A3B-IQ2_M.gguf -c 32768 --jinja -ngl 99
# Ollama (recent build that supports qwen35moe):
ollama create agentworld-32k -f Modelfile.32768 && ollama run agentworld-32k
Recommended sampling: temperature 1.0, top_p 0.95 (this is a reasoning model — low temp causes repetition loops). It emits a <think> reasoning channel; --jinja parses it into reasoning_content and tool calls into native tool_calls.
Agentic use: it makes native OpenAI tool calls out of the box with --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).Model, weights, training: © Qwen / Alibaba — Qwen/Qwen-AgentWorld-35B-A3B. Quant (IQ2_M + imatrix) + context Modelfiles + eval: KikoCis. apache-2.0 (same as upstream). No weights modified beyond quantization; text-only (vision tower not converted).