GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
0xSero
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
0xSero
Model Tree
deepseek-ai/DeepSeek-V4.1-Flash-1017
Input Modalities
Output Modalities
Supported Functionality
KL divergence against the native 1017 model, teacher-forced on sudoingX's KLD panel (199 conversations, 254,846 scored
assistant positions, sha256 39e0db2f…). The reference is DeepSeek's own inference/model.py, streamed layer by
layer on an H200.
| metric | value |
|---|---|
| KLD, mean over positions (nats) | 0.0304 (95 % CI 0.0268-0.0343) |
| KLD, 8 domains weighted equally | 0.0512 |
| KLD p99 | 0.435 |
| top-1 agreement | 94.95 % |
| panel perplexity, native -> this quant | 1.6010 -> 1.6231 |
| domain (share of positions) | KLD | top-1 |
|---|---|---|
| code (65 %) | 0.0182 | 95.83 % |
| math (4 %) | 0.0230 | 94.72 % |
| agentic (7 %) | 0.0277 | 94.96 % |
| long context (6 %) | 0.0379 | 95.20 % |
| knowledge (6 %) | 0.0568 | 92.05 % |
| writing (2 %) | 0.0795 | 91.56 % |
| multilingual (3 %) | 0.0827 | 93.35 % |
| chat (7 %) |
sudoingX's 2.7 bpw quant of the previous checkpoint (2cba9e42) scores 0.0243 / 95.57 % on the same panel at the
same budget. Because the base models differ, that is context, not a head-to-head result. The panel's replies were
written by the previous checkpoint. 1017 also showed 1.75-3.7x more EXL3 error energy per bit width than the previous
checkpoint in our measurements.
| part | encoding |
|---|---|
| 15,360 routed experts (layers 0-39) | EXL3, per expert K2 / K3 / K4 / K5 = 6,278 / 7,447 / 1,600 / 35; super experts K5, layers 37-39 at K3 or more (exl3_moe_plan.json) |
| attention + shared-expert linears | EXL3 K4 (wo_a K5) |
| LM head | EXL3 K4 |
DSpark drafter (mtp.0-2) | official precision (FP8 / MXFP4) |
| norms, router, embeddings, vision, compressors | official 1017 tensors |
| Engram tables (203 GB) | not included: download DeepSeek's two shards into the same folder (below) |
About 199 GB in this repo (110 files). MANIFEST.sha256 covers every file, including the two Engram shards.
927 sequences, 1,216,384 tokens, all native DeepSeek-V4.1-Flash-1017 replies (no output cap) in 2,048-token windows. Token shares: agentic 35 %, coding 25 % (TypeScript, Rust, Go, C, C++, HTML, math), religion and philosophy 20 %, multilingual 10 %, structured output 10 %, plus 1.4 % random tokens so rarely routed experts see inputs. The KLD panel is disjoint from it.
Use sudoingX's v1.1 serving stack (vLLM 6e517b15 for sm_121, patch series, exllamav3 1.6.0, vllm_exl3_moe
plugin). A CI-built, attested image of it is ghcr.io/sybil-solutions/deepseek-v4.1-flash-exl3-spark.
bash
# both Sparks, same absolute path, about 400 GB freehf download 0xSero/DeepSeek-V4.1-Flash-1017-EXL3-2.7bpw --local-dir ~/models/dsv41-1017-exl3hf download deepseek-ai/DeepSeek-V4.1-Flash-1017 model-00047-of-00048.safetensors model-00048-of-00048.safetensors \ --revision 1bae0e1088993b9b82de08f59de5be5a34e42170 --local-dir ~/models/dsv41-1017-exl3(cd ~/models/dsv41-1017-exl3 && sha256sum -c MANIFEST.sha256) # control machine with passwordless ssh to bothgit clone https://github.com/sudoingX/dgx-spark-deepseek-v41 ~/dsv41_recipe && git -C ~/dsv41_recipe checkout cc59c360IMAGE=ghcr.io/sybil-solutions/deepseek-v4.1-flash-exl3-spark@sha256:5817414f92e9bec0406dfc4575e16b282209f0cb1ead16fe53d51bac7ac9e9e4 \HEAD=<rank-0 host> WORKER=<rank-1 host> MODEL_DIR=$HOME/models/dsv41-1017-exl3 \ ~/dsv41_recipe/scripts/launch/dsv41_tp2.sh upThe API is OpenAI-compatible on :8000 with DeepSeek-V4.1 reasoning and tool-call parsing, a 262,144-token context and DSpark speculative decoding. Serving status and measured speed: see the recipe repo.
| 0.0835 |
| 90.68 % |