Drilldown: Recipe
More actions
Recipe > decode tps:
70-100 
& source :
https://github.com/iIIusi0n/qwen3.8-flash-next-cmp170hx or
Other
& source :
https://github.com/iIIusi0n/qwen3.8-flash-next-cmp170hx or
Other Use the filters below to narrow your results.
page:
DeepSeek V4 Flash 0731 on 3x 8 GB (PP3 DSpark) (1) ·
DeepSeek V4 Flash 0731 on 4x 8 GB (allover326 PP4 DSpark) (1) ·
DeepSeek V4.1 Flash on 4x 8 GB plus RTX PRO 6000 (ExLlamaV3 TP5) (1) ·
DeepSeek V4.1 Flash on 6x 8 GB (TP6) (1) ·
GLM 5.3 Flash on 4x 8 GB (kaka86mm EXL3 + Marlin sidecar + DFlash2) (1) ·
Qwen3.8 Flash Next on 2x 8 GB (vektorprime PP2) (1) ·
Qwen3.8 Flash Next on 3x 8 GB (clee PP3) (1) ·
Qwen3.8 Flash Next on 3x or 4x 8 GB (zebgop-ops FP8 PP) (1)
model:
quant:
AWQ INT4: cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4; 95 GiB BF16 PLE table in host RAM (FP8 table optional) (1) ·
EXL3 3.5 bpw (LibertAIDAI; routed experts 4 bpw on layers 0-9 and 30-39, 3 bpw on 10-29; attention and shared experts 6 bpw) plus the official Engram shards (1) ·
EXL3 4 bpw (Mia-AiLab/GLM-5.3-Flash-EXL3-TR3-4bpw, 164 GB) plus an offline-generated Marlin INT4 decode sidecar (151 GB) (1) ·
Native MXFP4 experts + FP8 attention (official deepseek-ai checkpoint, about 155.4 GiB); KV cache fp8 (2) ·
Official block FP8, about 126 GiB including the about 50 GiB FP8 n-gram (PLE) table, which is served from host RAM; KV cache bf16 (the QSA layers refuse fp8) (1) ·
Official checkpoint: dense MXFP8 through an SM80 Marlin W8A16 path, routed experts MXFP4 through W4A16; KV FP8 (1) ·
W4A16 AutoRound: Intel/Qwen3.8-Flash-Next-W4A16-AutoRound; 95.4 GiB BF16 PLE table streamed from NVMe; KV fp8 e4m3 (software-decoded on SM80) (1)
engine:
Custom SM80 vLLM (patched from public commit 79a7108d9) (1) ·
ExLlamaV3 fork (anoane/exllamav3-anemone) + TabbyAPI fork (anoane/tabbyAPI) (1) ·
vLLM nightly + PR #53899 (a5530b9) + the repo's patch scripts (1) ·
vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) (1) ·
vLLM: haosdent/vllm branch dsv4-flash-a100 plus allover326's 7 patches (DSpark under PP, sm_80 prefill top-k fallback, logits row chunking) (1) ·
vLLM: haosdent/vllm branch dsv4-flash-a100 with a vendored copy of allover326's 7 patches (image dsv4-a100:devel) (1) ·
vLLM: hyd998877/vllm_170hx_glm53-flash-exl3-optimized with kaka86mm's overlay patches; exllamav3 1.4.8 (1) ·
vLLM: the vllm/vllm-openai:qwen38-flash-next image with zebgop-ops patches 0001 to 0016 (never 0008-WITHDRAWN) and three ported files (1)
engine version:
0.1.dev1+ga5530b90c.d20260829 (1) ·
0.1.dev20073+g8e685d198; repo commit 2f551bb (patch 0016, 2026-10-02) (1) ·
base c3046d1 (recommended since 2026-08-13; first released on f8ea5bb); repo commit 3dd2d88 (1) ·
f8ea5bb-era base with the allover326 patch set as of mid-August 2026 (1) ·
final production build v30 (numbers measured on v24); repo commit 218b47f (1) ·
q38fn/stack on nightly-7d0b4e57 (1) ·
reports 0.0.0; patches/public-base-to-runtime.patch (109 files) (1) ·
tag recipe-09 (309ef6d1); TabbyAPI deepseek-v41 (ce250ff) (1)
cards:
topology:
PP2 with PLE CPU offload (1) ·
PP3 (VLLM_PP_LAYER_PARTITION=15,15,13) with DSpark, 5 draft tokens; PCIe Gen2 x4, no P2P (1) ·
PP3, no P2P (works at PP2 on two cards) (1) ·
PP4 (VLLM_PP_LAYER_PARTITION=12,12,12,7) with DSpark, 5 draft tokens; PCIe Gen2 x4, no P2P (1) ·
PP4 (VLLM_PP_LAYER_PARTITION=13,11,11,10), DFlash2 k=7; PCIe Gen2 x4, no P2P (1) ·
PP4, VLLM_PP_LAYER_PARTITION=12,12,12,12, MTP 3, FULL_AND_PIECEWISE CUDA graphs; PCIe Gen2 x4 per card, no P2P. Three cards: PP3 with 16,17,15 or 16,16,16 (1) ·
TP5 across four CMP 170HX and one RTX PRO 6000 Blackwell (native backend, reduces through host memory); MTP draft on the PRO (1) ·
TP6 (virtual-head padding), PP1 (1)
context:
1,047,736 verified one-shot; 1,002,852 over a 405-turn chat with DSV4_LOGITS_ROW_CHUNK=64 (1) ·
1,048,576 (1) ·
1,048,576 (YaRN x4) (1) ·
1,048,576 FP16 (1) ·
262,144 (1) ·
262,144 native; 524,288 with YaRN 2.0; 1,048,576 with YaRN 4.0 (needle verified on PP3) (1) ·
524,288 (1) ·
691,968 (largest stable context at --gpu-memory-utilization 0.965) (1)
decode tps:
vram per card:
64 GB (65,536 MiB), --gpu-memory-utilization 0.965 (1) ·
64 GB, --gpu-memory-utilization 0.85 (1) ·
64 GB, --gpu-memory-utilization 0.93 (0.94 is the ceiling) (1) ·
64 GB, --gpu-memory-utilization 0.95 (1) ·
64 GiB, gpu-memory-utilization 0.92 (1) ·
64 GiB; --gpu-memory-utilization 0.94 plus per-rank KV budgets; measured 34.0-34.3 GiB per 12-layer rank, 37.9 GiB on the drafter rank (1) ·
64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 (1) ·
gpu_split 58 GB per CMP, 70 GB on the PRO (1)
power cap:
driver:
unlock build:
status:
tested by:
tested on:
source: (Click arrow to add another value)
Showing below up to 8 results in range #1 to #8.