GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
The-freezer
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
The-freezer
Model Tree
The-freezer/GLM-5.2-DERISKED-NVFP4
Input Modalities
Output Modalities
Supported Functionality
The full-precision GLM-5.2 de-risked master is ~1.35 TiB and needs an 8×B200-class node. The NVFP4 build brings that to ~451 GB. This build goes further — a non-uniform REAP prune on top of NVFP4, landing at ~323 GB, roughly 28% smaller than its NVFP4 parent and about a quarter of the BF16 master.
The point is footprint. If the NVFP4 build is close but doesn't fit your envelope, this is the one to ask about.
| Architecture | GlmMoeDsaForCausalLM — GLM MoE with MLA + DeepSeek-style Sparse Attention |
| Base | zai-org/GLM-5.2 — official |
| Parent | GLM-5.2-DERISKED-NVFP4 |
| Transform | Refusal-direction de-risk (in parent) → NVFP4 → non-uniform REAP prune |
| Keep set | NU176 — non-uniform, per-layer budgets rather than a flat keep |
| Precision | NVFP4 (4-bit floating-point, microscaled, two-level block scaling) |
| On-disk | ~323 GB · 65 safetensors shards |
| Languages | English, Chinese |
| Serving | vLLM |
| Status | EXPERIMENTAL — unbenchmarked |
REAP is router-weighted expert activation pruning: experts are scored by their contribution
across a calibration set, and the least-salient are dropped.
NU denotes a non-uniform keep — the per-layer budget varies with measured routing load rather
than removing the same count from every MoE layer. Layers that genuinely spread work across many
experts keep more of them; layers whose routing concentrates keep fewer. That buys a better
capability-per-byte trade than a flat prune at the same total size, at the cost of less predictable
per-layer memory.
Contrast with the Kimi K3 line, where
KIMI-K3-DERISKED-CODER-REAP-320-MXFP4
uses a uniform 320-of-896 keep specifically so memory and routing stay predictable layer to layer.
Both approaches are available; which is right depends on whether you are optimising for quality at a
size target or for predictability.
text
zai-org/GLM-5.2 official open-weight, 256 routed experts └─ GLM-5.2-DERISKED-BF16 in-house refusal-direction de-risk, from source └─ GLM-5.2-DERISKED-NVFP4 NVFP4 quantization └─ GLM-5.2-DERISKED-REAP-NU176-NVFP4 ← this repo, non-uniform REAP prune| Applied | Weight-level de-risk (in BF16 master) · NVFP4 quantization · non-uniform REAP prune |
| Not applied | SFT · DPO · RLHF |
| Format | HF safetensors · NVFP4 |
On refusal behaviour: this checkpoint inherits the parent's deliberately reduced refusal surface. It is a Blackfrost de-risked model. Do not evaluate or rate-limit it as if it were a safety-stock derivative of upstream GLM-5.2.
| Benchmark | GLM-5.2-DERISKED-NVFP4 | This (REAP-NU176) | Retention |
|---|---|---|---|
| pending | — | — | —% |
Expert pruning is a capability trade, and a card that ships a pruned build without publishing what it cost is asking the reader to take the trade on faith. Harness, conditions and retention figures will be stated here — including any benchmark where retention is poor.
Two things specifically unmeasured on this checkpoint:
Until both are measured, the parent's numbers should not be quoted for this build.
max_tokens generously.Blackfrost publishes the GLM-5.2 de-risked line in several shapes. Public GLM-5.2 and GLM-5.3 releases are free and ungated. Private releases and custom engineering remain separately scoped.
| Build | What it is |
|---|---|
GLM-5.2-DERISKED-BF16 | Full-precision BF16 master — every other build in this line derives from it |
GLM-5.2-DERISKED-NVFP4 | 4-bit NVFP4, single-node serving on sm_120-class hardware |
| This repo | Non-uniform REAP prune on top of NVFP4 — smallest footprint in the line |
| Custom | Expert budgets, uniform or non-uniform keep sets, or de-risking calibrated against your own threat model |
For custom engineering or deployment support, contact @Blackfrost_AI.
Refusal behaviour in this checkpoint has been deliberately modified at the weight level. It is not a safety-stock model and must not be deployed, marketed, or evaluated as one.
Capability has been deliberately reduced. Experts were removed by non-uniform prune. The size of that reduction has not been measured on this checkpoint. Do not assume parent-equivalent quality.
No warranty of any kind. Provided "as is", without warranty express or implied, including fitness for a particular purpose. Nothing here guarantees that any given input will be accepted or refused, that any capability is retained, or that any category of output is unreachable.
No measurements are published for this build. Figures on the parent card describe the parent, under its own stated harness and caveats, and do not transfer here.
Modification by a recipient voids this characterization. Blackfrost's obligations attach at the point of release. Any further ablation, fine-tuning, merging, quantization or alteration by a recipient produces an artifact Blackfrost has not evaluated and does not stand behind — responsibility for that artifact transfers entirely to whoever produced it.
Operator-owned policy. Open weights mean the operator sets and enforces policy. Deploy only in controlled environments with access control, independent logging and review.
Free and ungated — download directly without payment or an access request.
Free public download: The-freezer/GLM-5.2-DERISKED-REAP-NU176-NVFP4. No payment, sign-in, or access request is required to download the weights. Existing repository and upstream license terms still apply.
zai-org/GLM-5.2 — upstream terms travel with this derivative.zai-org/GLM-5.2 official open-weight, 256 routed experts └─ GLM-5.2-DERISKED-BF16 in-house refusal-direction de-risk, from source └─ GLM-5.2-DERISKED-NVFP4 NVFP4 quantization └─ GLM-5.2-DERISKED-REAP-NU176-NVFP4 ← this repo, non-uniform REAP prune