Drilldown: Recipe
More actions
Recipe > status:
Proven 
& source :
https://github.com/mannydelrio/qwen38-flash-next-2x-cmp170hx or
Other
& source :
https://github.com/mannydelrio/qwen38-flash-next-2x-cmp170hx or
Other Use the filters below to narrow your results.
page:
DeepSeek V4 Flash 0731 on 4x 8 GB (allover326 PP4 DSpark) (1) ·
DeepSeek V4.1 Flash on 4x 8 GB (GNmac) (1) ·
GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 layer split) (1) ·
GLM 5.3 Flash on 4x 8 GB (1) ·
GLM 5.3 on 8x 8 GB (vllm-170hx-glm5) (1) ·
Qwen3.8 27B on 1x 8 GB (W4A16 vLLM) (1) ·
Qwen3.8 Flash Next on 1x 8 GB (iIIusi0n SSD PLE) (1) ·
Qwen3.8 Flash Next on 2x 8 GB (ElectroHobo W4A16 TP2) (1) ·
Qwen3.8 Flash Next on 3x 8 GB (clee PP3) (1) ·
Sandbox/Import smoke test (1)
model:
quant:
AutoRound 3 bpw + MTP: klee100/Qwen3.8-Flash-Next-AutoRound-3bpw-MTP; 95.37 GiB BF16 PLE table on SSD (1) ·
AWQ 4-bit (1) ·
EXL3 3.05 bpw: turboderp/GLM-5.3-Flash-exl3 (1) ·
GLM-5.3-Int4-Int8Mix-AWQ-g64; drafter incoai/GLM-5.3-DFlash2 (1) ·
Hybrid: routed experts EXL3 (mostly 3 bpw, 2 bpw on layers 18-22) from LibertAI's 2.9 bpw pack; attention, shared experts, indexer and DSpark drafter official FP8; KV fp8_ds_mla (1) ·
Native MXFP4 experts + FP8 attention (official deepseek-ai checkpoint, about 155.4 GiB); KV cache fp8 (1) ·
W4A16 (INT4 weights, group size 128, FP16 activations): canada-quant/GLM-5.3-Flash-W4A16-MTP (1) ·
W4A16 (INT4 weights, Marlin kernels) (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) ·
W4A16: halt95/Qwen3.8-Flash-Next-W4A16-Merlin (AutoRound INT4 g128 experts, INT8 GDN projections, FP8 n-gram table) (1)
engine:
ExLlamaV3 1.5.4 (built for SM80) with a small OpenAI-compatible server (1) ·
Morrowmake/vllm-cmp170hx (vLLM fork, container image) (1) ·
Morrowmake/vllm-cmp170hx branch ampere-glm53 plus fail-closed source patches (1) ·
Morrowmake/vllm-cmp170hx image (Qwen EXL3 release) with patch files mounted read-only (1) ·
vLLM (1) ·
vLLM a5a30471 plus a 13-file downstream patch (native Linux AIO PLE reader) (1) ·
vLLM fork (1) ·
vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) (1) ·
vLLM with a pinned sm_80 patch stack (built locally from source) (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)
engine version:
None (1) ·
0.0-smoke (1) ·
0.29.1rc1.dev402+ga5a30471f.ple1 (1) ·
base c3046d1 (recommended since 2026-08-13; first released on f8ea5bb); repo commit 3dd2d88 (1) ·
Flun/glm53-flash-cmp170hx-exl3 at 5933112 (1) ·
q38fn/stack on nightly-7d0b4e57 (1) ·
recipe 0.3.1; engine 18305948ac (1) ·
recipe 1.2.0 (1) ·
recipe 1.8.0, engine 819146023f (1) ·
vLLM 0.30.1rc1, fork commit 378c37b0 (1)
topology:
layer split (no tensor parallel), 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) ·
PP8 (also PP9 and PP10), TP1 (1) ·
single card (2) ·
TP2 with whole-expert expert parallel (1) ·
TP4 (1) ·
TP4 (default) or PP4 (1) ·
TP4 (default) or PP4 for x1/x4 links (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 (YaRN x4) (1) ·
1,048,576 per request (1) ·
262,144 (2) ·
262,144 (up to 1,048,576) (1) ·
262,144 advertised (tested through 32K) (1) ·
262,144 native (YaRN to about 500k in the recipe's long variant) (1) ·
32768 (1) ·
392,960 (profile q8_384k) (1)
decode tps:
prefill tps:
vram per card:
1 GB (1) ·
64 GB (1) ·
64 GB, --gpu-memory-utilization 0.85 (1) ·
64 GiB exposed, --gpu-memory-utilization 0.95 (1) ·
64 GiB, --gpu-memory-utilization 0.96 (1) ·
64 GiB, gpu-memory-utilization 0.92 (1) ·
64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1) ·
64 GiB, GPU_UTIL 0.95 (fixed) (1) ·
64 GiB, GPU_UTIL 0.96 at PP8 (1) ·
about 58 GiB of 64 GiB (116.6 GiB resident across both) (1)
power cap:
driver:
unlock build:
status: (Click arrow to add another value)
tested by:
tested on:
source: (Click arrow to add another value)
Showing below up to 10 results in range #1 to #10.