GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
cloudsurf-software
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
cloudsurf-software
Model Tree
google/gemma-4-E4B-it
Input Modalities
Output Modalities
Supported Functionality
| Overall | Non-Live | Live | Multi-Turn | Web | Memory | Irrelevance | |
|---|---|---|---|---|---|---|---|
| CloudSurf-4B-FC (3-seed mean) | 55.73 | 87.23 | 79.82 | 43.46 | 48.00 | 41.65 | 80.63 |
| Stock gemma-4-E4B-it (×3 mean) | 34.81 | 84.30 | 73.97 | 19.46 | 7.00 | 16.56 | 84.37 |
Raw result files for every run in this table — ours and the stock baselines, plus per-category scores and a comparison chart — are public: CloudSurf-4B-FC-bfcl-results.
Seeds {42, 7, 11} → {55.53, 54.86, 56.81}, spread 1.95. Best-checkpoint (seed 11) re-eval: two further same-box FULL evals returned 54.39 and 54.91 — measured same-checkpoint eval band {56.81, 54.39, 54.91}, mean 55.37, sd ≈ 1.05 (per-run BFCL FULL eval noise on this model class is ≈ ±1; single runs < ~2.5 apart are not meaningfully different). Every measured number, including the weakest (54.39), exceeds the published small-model class bar (Nanbeige4-3B, 51.40) and stock by double digits. Contamination-audited clean (0/255 eval-prompt 8-gram overlap; behavioral trace verification).
Serving-variant fairness pair (pre-registered, measured 2026-08-17):
stripping stray <tool_call|> closers — a decode artifact of the base's
native prior — raises STOCK to 39.40 (Multi-Turn 19.46 → 33.12) and moves
this model +0.52 (→ 54.91). Under that matched best-serving frame the honest
comparison is 54.91 vs 39.40 (+15.5); the as-registered frame is 55.73
vs 34.81 (+20.9). Both are reported everywhere; the strip ships in the
proposed BFCL handler for all Gemma-4 prompt-mode models.
Honesty disclosures (full apparatus in the forthcoming paper):
<tool_call|>
closer strip, which also rescues stock's native decode quirk) was
measured 2026-08-17 and is disclosed above (54.91 vs 39.40); headline
numbers use the registered handler.7f8711e00f66bad0) — state-verified
gpt-oss-120b teacher trajectories (partially-observable look-then-act envs),
memory-discipline conversations, irrelevance-refusal rows; teacher reasoning
retained in the thought channel.<turn|>). Full apparatus in the forthcoming paper.merged/ — BF16 merged champion checkpoint (seed 11).adapters/seed-{42,7,11}/ — the three LoRA adapters (111M each) for
repeatability; merge with peft or scripts/fastloop_merge_adapter.py.The model's native interface is prompt-mode (Gemma-4 turn format, bracket
tool-call lists). For harnesses that speak the OpenAI chat/tools API —
including tau2-bench — this
repo ships the exact serving bridge used for our τ²-bench leaderboard runs:
serving/fc_tau2_bridge.py (stdlib-only, no
dependencies). Full τ²-bench trajectories (retail / airline / telecom, ×4
trials, unmodified) are public:
tau2-trajectories-cloudsurf-4b-fc.
bash
# 1) serve the merged weights with any /v1/completions backend, e.g. sglang:python -m sglang.launch_server --model-path cloudsurf-software/CloudSurf-4B-FC \--revision main --port 30000 # serve the merged/ subtree# 2) put the bridge in front (OpenAI-compatible /v1/chat/completions, tools in / tool_calls out):python serving/fc_tau2_bridge.py --port 8000 --backend http://127.0.0.1:30000# 3) point any OpenAI client at http://127.0.0.1:8000/v1 (model id: cloudsurf-4b-fc)python serving/fc_tau2_bridge.py --selftest # render/parse self-checks
Disclosure (mirrors our τ²-bench submission methodology): the bridge appends a fixed function-calling instruction block to the caller's system message, and when a generation terminates inside the thought channel with an empty answer it attempts to recover a bracket-format tool-call list from the raw text before returning an empty answer. Both behaviors are in the script, unabridged.
Earlier revisions of this repository shipped a model.safetensors missing 54
tensors relative to the base model: k_proj, v_proj, and k_norm weights
for language-model layers 24–41 (2076 keys instead of 2130). These layers use
shared KV projections (num_kv_shared_layers: 18), and the export path
(transformers 5.15.0 save_pretrained) silently omitted their parameters.
Some engines tolerated the omission; vLLM 0.25.1 correctly refused to load
the checkpoint.
The current revision restores all 2130 tensors. The 54 restored tensors are
byte-exact copies from google/gemma-4-E4B-it — this is provably lossless:
the fine-tuning adapter contains no LoRA entries for k/v projections at or
above layer 24, and every one of the 2076 retained tensors is either
bit-identical to the base or accounted for by an adapter-targeted module.
config.json now matches the base model's schema so the checkpoint loads
under both current and older transformers versions.
Verification: the fixed checkpoint serves under vLLM 0.25.1, and greedy decoding logprobs match an independently reconstructed base+adapter merge at the same numerical floor measured between two servings of the unmodified base model (top-1 agreement 99.6% vs a 98.8% same-model cross-engine control; max chosen-token logprob difference 0.166 vs 0.126 control).