GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
LiamVisionary
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
LiamVisionary
Model Tree
google/gemma-4-12B-it
Input Modalities
Output Modalities
Supported Functionality
Want to build and manage an entire private swarm of agents? HivemindOS gives you shared memory, reusable skills, one-time setup, and a superbrain architecture for coordinating agent work.
The upstream model card reports a strong relative gain on local tau2-bench telecom-style agentic tool-use compared with google/gemma-4-12B-it; see the upstream card for methodology and caveats.
Local verified artifact:
200/60.0086798667907714840/6 strict full-response refusals0/6 strict full-response refusalsThe strict check measures refusal behavior on a small local prompt set. It is not a complete safety, misuse, or quality benchmark. Add application-level guardrails where needed.
The verified hosted endpoint for this release serves the companion GGUF repo through llama.cpp on Modal as an OpenAI-compatible API.
Recommended served model name:
text
swarm-scout-12b
The hosted Modal proxy accepts the previous swarm-sovereign-scout-12b alias for compatibility, but new clients should request swarm-scout-12b.
The deployment uses the companion GGUF artifacts:
text
LiamVisionary/swarm-sovereign-scout-12b-GGUFswarm-sovereign-scout-Q4_K_M.ggufMTP/gemma-4-12B-it-MTP-Q8_0.ggufmmproj-swarm-sovereign-scout-bf16.ggufchat_template.jinja
Verified Modal serving path:
server-cuda-b9870draft-mtp--spec-draft-n-min 0 --spec-draft-n-max 2mmproj-swarm-sovereign-scout-bf16.ggufvLLM was tested first, but the available vLLM path did not load this Gemma 4 unified/assistant combination reliably. Use the GGUF/llama.cpp route unless vLLM adds compatible support for this model family.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchrepo = "LiamVisionary/swarm-sovereign-scout-12b"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo,torch_dtype=torch.bfloat16,device_map="auto",)messages = [{"role": "user", "content": "Write a small Python LRU cache."}]inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=512, do_sample=False)print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
Use a recent transformers build with Gemma 4 unified architecture support.
The local/runtime GGUF release is published separately at:
text
LiamVisionary/swarm-sovereign-scout-12b-GGUF
That repo includes:
swarm-sovereign-scout-Q4_K_M.ggufMTP/gemma-4-12B-it-MTP-Q8_0.ggufmmproj-swarm-sovereign-scout-bf16.ggufchat_template.jinjaLocal llama.cpp MTP speculative decoding was verified with llama.cpp b9553 and --spec-draft-n-min 0 --spec-draft-n-max 2. Modal serving was verified with llama.cpp server-cuda-b9870.
The underlying Gemma 4 unified configuration includes image/video/audio processor metadata. The companion GGUF release now includes a tested llama.cpp projector artifact:
text
mmproj-swarm-sovereign-scout-bf16.gguf
Verified on 2026-07-05:
b9553 loaded the Q4_K_M GGUF plus the projector.server-cuda-b9870 advertised multimodal capability.Merchant: SWARM CAFE. Total: $8.37. from a receipt image.Image input is verified. The projector metadata also exposes an audio encoder, but audio/video input was not separately quality-tested for this release.
google/gemma-4-12B-ityuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUFReleased under Apache 2.0, following the upstream/base lineage.