GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
patrickbdevaney
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
patrickbdevaney
Model Tree
zai-org/GLM-5.3-Flash
Input Modalities
Output Modalities
Supported Functionality
| Property | Original (zai-org/GLM-5.3-Flash) | This model (REAP-50) |
|---|---|---|
| Total parameters | ~301 B | ~157 B |
| Active parameters / token | ~12.5 B | ~12.5 B (unchanged) |
| Layers | 78 (3 dense + 75 MoE) | 78 (3 dense + 75 MoE) |
| Routed experts / MoE layer | 256 | 128 (50% pruned) |
Active experts / token (num_experts_per_tok) | 8 | 8 |
| Shared expert / MoE layer | 1 | 1 (untouched) |
| Attention | MLA + DSA (deepseek_v32, kv_lora_rank=512, q_lora_rank=2048, index_topk=2048) | Untouched |
| Context length | 202,752 | 202,752 |
| Size | 296 GiB (FP8) | 157.0 GiB (FP8) |
| License | MIT | MIT |
Each MoE layer l in [3..77] has 256 routed SwiGLU experts (gate_proj, up_proj, down_proj, intermediate size 1536) routed by a sigmoid gate (routed_scaling_factor = 2.5, norm_topk_prob = true, e_score_correction_bias).
calibration_tokens.pt, SHA-256 recorded in reap_plan.json).bfloat16 using the exact deepseek_v32 MLA + rotary + lightning-indexer attention implementation and exact block-scale FP8 (F8_E4M3 x F8_E8M0 UE8M0) dequantization (saliency_pass.py).j in layer l, over the set T_j of calibration tokens where expert j is in the router's top-8:
text
S_j = (1 / |T_j|) * sum_{t in T_j} g_{t,j} * || down_proj_j( silu(gate_proj_j(h_t)) * up_proj_j(h_t) ) ||_2g_{t,j} is the normalized top-8 routing weight (prior to routed_scaling_factor, which is a constant multiplier across experts).S_j are retained in ascending original-index order kept = [k_0 < k_1 < ... < k_127]:
mlp.gate.weight ([256, 5120] -> [128, 5120]) and mlp.gate.e_score_correction_bias ([256] -> [128]) are sliced to kept.mlp.experts.{kept[new_idx]}.* are renamed to mlp.experts.{new_idx}.* (0..127) with zero modification to their F8_E4M3 weights or F8_E8M0 weight_scale_inv blocks.lm_head are copied bit-for-bit from zai-org/GLM-5.3-Flash.model.layers.78, num_nextn_predict_layers) is omitted (num_nextn_predict_layers = 0).Full per-layer keep/prune metadata and first-moment gains are included in ./reap_metadata.json and ./adapters/first_moment_gains.json, with the full pipeline source in patrickbdevaney/glm-5.3-reap.
Identical to zai-org/GLM-5.3-Flash: fine-grained FP8 (fp8 block [1, 128] with F8_E4M3 weights and F8_E8M0 weight_scale_inv), ready for drop-in serving with vLLM or SGLang (deepseek_v32 / GlmMoeDsaForCausalLM).
bash
# vLLM (2x 80GB+ GPUs, or 1x 192GB B200)vllm serve patrickbdevaney/GLM-5.3-Flash-REAP50-FP8 \ --tensor-parallel-size 2 \ --trust-remote-code \ --max-model-len 65536 # SGLangpython3 -m sglang.launch_server \ --model-path patrickbdevaney/GLM-5.3-Flash-REAP50-FP8 \ --tp 2 \ --trust-remote-code| Claim / Artifact | Primary Verification Source |
|---|---|
Upstream Base Model (301B FP8, MIT) | zai-org/GLM-5.3-Flash · ./LICENSE |
| Superseded By (v2 Domain-Balanced + MTP Layer 78) | patrickbdevaney/GLM-5.3-Flash-REAP50-FP8-v2 |
| In-Repo REAP Metadata & First-Moment Gains | ./reap_metadata.json · ./adapters/first_moment_gains.json |
| Model Config & 62-Shard Safetensors Index | ./config.json · ./model.safetensors.index.json · ./chat_template.jinja |
| REAP-50 Pipeline & Integrity Audit | patrickbdevaney/glm-5.3-reap (main @ 8540a0a) · EVAL_INTEGRITY.md |
Pure-CUDA Thor Engine (sm_110a) | patrickbdevaney/glm-5.3-flash-cuda-server (main @ 399a837) |
zai-org/GLM-5.3-Flash by Z.ai (MIT License, ./LICENSE).# vLLM (2x 80GB+ GPUs, or 1x 192GB B200)vllm serve patrickbdevaney/GLM-5.3-Flash-REAP50-FP8 \ --tensor-parallel-size 2 \ --trust-remote-code \ --max-model-len 65536 # SGLangpython3 -m sglang.launch_server \ --model-path patrickbdevaney/GLM-5.3-Flash-REAP50-FP8 \ --tp 2 \ --trust-remote-code