AutoTrust AI, Singapore · Released October 26, 2026Qwen3.8-Flash-Next E384 FP4 V2 at a glance
- Made by
- AutoTrust AI, Singapore
- Released
- October 26, 2026
- Parameters
- 149.2B, 6B active
- Context window
- 256K tokens
Qwen3.8-Flash-Next E384 FP4 V2 VRAM Requirements
AutoTrust AI, Singapore · Released October 26, 2026New
Qwen3.8-Flash-Next E384 FP4 V2 has 149.2B parameters (6B active per token). In BF16 its weights alone take 274 GiB; quantized to 4-bit, about 86.7 GiB. Each 32K-token request adds 0.77 GiB of KV cache. Cheapest way to run it today: 3 × GeForce RTX 3090 (24 GB) at $0.324 per hour.
Size your own setup in the calculator →VRAM by precision and context length
Weights plus the KV cache of one request (BF16 cache) and the model's fixed recurrent state, in GiB. Add 1 to 3 GiB for the inference engine itself.
| Weights format | Weights only | + 8K context | + 32K context | + 128K context | + 256K context |
|---|---|---|---|---|---|
| NVFP4 (native) | 78.0 | 78.3 | 78.9 | 81.2 | 84.3 |
| BF16 / FP16 | 274 | 274 | 275 | 277 | 280 |
| FP8 / INT8 | 138 | 139 | 139 | 141 | 145 |
| 4-bit (GGUF Q4_K_M) | 86.7 | 87.0 | 87.6 | 89.9 | 93.0 |
How many GPUs to run Qwen3.8-Flash-Next E384 FP4 V2
Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.
| GPU | NVFP4 (native) | BF16 / FP16 | 8-bit | 4-bit |
|---|---|---|---|---|
| GeForce RTX 4090 24 GB | Not on this GPU | 16 (several machines) | 5 | 3 |
| GeForce RTX 5090 32 GB | Not on this GPU | 7 | 4 | 2 |
| RTX PRO 6000 Blackwell 96 GB | Not on this GPU | 2 | 1 | 1 |
| Mac M5 Max 128 GB 96 GB usable | Not on this GPU | 2 | 1 | 1 |
| Ryzen AI Max+ 395 128 GB 96 GB usable | Not on this GPU | 2 | 1 | 1 |
| DGX Spark (GB10) 128 GB | Not on this GPU | 2 | 1 | 1 |
| NVIDIA H100 80 GB | Not on this GPU | 5 | 3 | 2 |
| NVIDIA H200 141 GB | Not on this GPU | 3 | 2 | 1 |
| NVIDIA B200 (HGX) 180 GB | 1 | 2 | 1 | 1 |
8-bit: FP8 with vLLM (INT8 on GPUs without FP8), Q8_0 with llama.cpp. 4-bit: AWQ / GPTQ with vLLM, Q4_K_M with llama.cpp, both counted at the Q4_K_M size. Not on this GPU: the official NVFP4 weights do not run there (llama.cpp needs a GGUF version, and vLLM needs a GPU with FP4 support).
Cheapest way to run Qwen3.8-Flash-Next E384 FP4 V2 today
For each GPU: the fewest cards that fit Qwen3.8-Flash-Next E384 FP4 V2 with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-11-06).
| Setup | Per hour | Weights | Provider | Per month | Rent |
|---|---|---|---|---|---|
| 3 × GeForce RTX 3090 24 GB | $0.324 | Q4_K_M | Vast.ai | $236.52 | Rent 3 × GeForce RTX 3090 on Vast.ai (opens in a new tab) → |
| 5 × RTX A4000 16 GB | $0.360 | Q4_K_M | Vast.ai | $262.80 | Rent 5 × RTX A4000 on Vast.ai (opens in a new tab) → |
| 3 × RTX A5000 24 GB | $0.567 | Q4_K_M | Vast.ai | $413.91 | Rent 3 × RTX A5000 on Vast.ai (opens in a new tab) → |
| 6 × NVIDIA L4 24 GB | $0.624 | 4-bit | Vast.ai | $455.52 | Rent 6 × NVIDIA L4 on Vast.ai (opens in a new tab) → |
| 2 × RTX A6000 48 GB | $0.644 | Q8_0 | Vast.ai | $470.12 | Rent 2 × RTX A6000 on Vast.ai (opens in a new tab) → |
| 3 × RTX PRO 4000 Blackwell 24 GB | $0.669 | Q4_K_M | Vast.ai | $488.37 | Rent 3 × RTX PRO 4000 Blackwell on Vast.ai (opens in a new tab) → |
| 2 × GeForce RTX 5090 32 GB | $0.802 | Q4_K_M | Vast.ai | $585.46 | Rent 2 × GeForce RTX 5090 on Vast.ai (opens in a new tab) → |
| 3 × GeForce RTX 4090 24 GB | $0.963 | Q4_K_M | Vast.ai | $702.99 | Rent 3 × GeForce RTX 4090 on Vast.ai (opens in a new tab) → |
On-demand prices from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.
AWS, Google Cloud and UpCloud prices: Spare Cores (opens in a new tab), CC BY-SA 4.0 (opens in a new tab), shared under the same license.
KV cache: how memory grows with context
Architecture: Qwen3.8-Flash-Next pruned to 384 experts · 12 Qwen Sparse Attention layers (GQA, 2 KV × 256, + indexer keys per 4-token block) · 36 Gated DeltaNet layers · 51B n-gram embeddings. Its KV cache is 3.9× smaller than if every layer used full attention, because it keeps only a short window of tokens at full detail and compresses the rest of the sequence. Only 6B parameters are active per token, but all 149B must sit in memory: VRAM depends on the total, speed on the active part.
| Context per request | BF16 cache | FP8 cache |
|---|---|---|
| 8K tokens | 0.19 GiB | 0.10 GiB |
| 32K tokens | 0.77 GiB | 0.40 GiB |
| 128K tokens | 3.09 GiB | 1.59 GiB |
| 256K tokens | 6.19 GiB | 3.19 GiB |
Plus 110 MiB of recurrent state per request, whatever the context.
Qwen3.8-Flash-Next E384 FP4 V2 VRAM FAQ
How much VRAM does Qwen3.8-Flash-Next E384 FP4 V2 need?
In BF16 the weights alone take 274 GiB (294 GB). In FP8 that is 138 GiB, and about 86.7 GiB with 4-bit quantization (Q4_K_M); the official NVFP4 checkpoint is 78.0 GiB. Each request then adds KV cache: 0.19 GiB at 8K tokens and 0.77 GiB at 32K (BF16 cache).
Can Qwen3.8-Flash-Next E384 FP4 V2 run on a single RTX 4090 (24 GB)?
No. Even in 4-bit it needs 3 RTX 4090s. In 4-bit it fits on a single RTX PRO 6000 Blackwell (96 GB).
Can Qwen3.8-Flash-Next E384 FP4 V2 run on an RTX 5090 (32 GB)?
No. Even in 4-bit it needs 2 RTX 5090s.
Can Qwen3.8-Flash-Next E384 FP4 V2 run on a Mac?
Yes. In 4-bit (Q4_K_M with llama.cpp) it needs a Mac with 96 GB of unified memory or more, of which macOS gives the GPU about 72 GB, for one request with an 8K-token context. In 8-bit (Q8_0) it needs 128 GB or more.
Can Qwen3.8-Flash-Next E384 FP4 V2 run on a DGX Spark or a Ryzen AI Max+ 395 (128 GB)?
Yes. In Q8_0 (139 GiB with an 8K-token context) it fits on a DGX Spark (128 GB) and on a Ryzen AI Max+ 395 with 128 GB, whose GPU gets up to 96 GB, with llama.cpp and one request.
What is the cheapest way to run Qwen3.8-Flash-Next E384 FP4 V2?
On 2026-11-06, the cheapest on-demand setup is 3 × GeForce RTX 3090 (24 GB) with Q4_K_M weights on Vast.ai, at $0.324 per hour (about $236.52 per month). Next: 5 × RTX A4000 (16 GB) with Q4_K_M weights on Vast.ai, at $0.360 per hour. Sized for one 8K-token request; prices are checked every hour.
How many H100 GPUs does Qwen3.8-Flash-Next E384 FP4 V2 need?
With one request and an 8K-token context: 5 in BF16, 3 in FP8 and 2 in 4-bit (vLLM, 90% of memory usable). Serving many users at once needs more memory for their KV caches: the calculator sizes that for you.
Qwen3.8-Flash-Next E384 FP4 V2 VRAM badge
For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/qwen3-8-flash-next-e384-fp4-v2.json.
[](https://studiotvai.com/vram-requirements/qwen3-8-flash-next-e384-fp4-v2)Other models
Same family (hybrid linear attention): Qwen3.5 4B · MiniCPM-V-4.7 1B · Raon-1 mini preview · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Clover 35B-A3B Preview · SenseNova Loop 9B Preview · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · LFM3 1.7B · LFM3-VL 2B · d1 2B · LFM2.5 8B-A1B · LFM2 24B-A2B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Clef · Clef Flash · d1 3B · JEV 27B VL · LightOnOCR-3 4B · Agnes-3.0-Qwen · Agnes-3.0-Flash · Qwen3.6 27B · Qwen3.5 27B · Qwen3.5 35B-A3B · MiniCPM-V-4.7 35B-A3B · LFM2.5 24B-A2B · Ornith-1.5 122B · Sage-A1.5 · MLExpert · Agents-A1 4B · Ling-3.0-flash-Sante · MiniCPM-OCR-1.0 · Qwen3.5 4B-Qwenputer · 6.8-Code2Video · Qwen3-Next 80B-A3B
All 212 other models
Llama 3.1 8B · Llama 3 8B · Llama 3.2 3B · Nanbeige4.3 33B · Granite 4.2 30B · Granite 4.2 8B · Granite 4.2 3B · MiniCPM5 2B · MiniCPM5 1B · Ministral 3 14B · Ministral 3 8B · Ministral 3 3B · Devstral 2 123B · Devstral Small 2 24B · Mistral Medium 3.5 128B · Magistral Small 1.2 24B · Mistral Small 3 24B · Mistral Large 2411 123B · Pixtral Large 124B · Codestral 22B · Mistral Small 2409 22B · Pixtral 12B · Nemotron 3.5 Parse · Gemma 2 9B · Gemma 3 4B · Gemma 3 12B · Gemma 3 27B · LLaVA 1.6 Mistral 7B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 70B · Llama 3.1 405B · Hy-Memory 30B-A3B · Kimi VL A3B Instruct · Mixtral 8x7B · Unlimited-OCR · Unlimited-OCR 2 · Xing4.0 29B-A4B · Qwen3.5 4B · MiniCPM-V-4.7 1B · Raon-1 mini preview · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Clover 35B-A3B Preview · SenseNova Loop 9B Preview · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · LFM3 1.7B · LFM3-VL 2B · d1 2B · LFM2.5 8B-A1B · LFM2 24B-A2B · Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Scout 17B-16E · Llama 4 Maverick 17B-128E · Kolibri-1 · Recursive Flint · Nemotron Labs Dory 1.0 4B · Step 3.5 Flash · Step 3.7 Flash · Laguna S 2.1 · Laguna XS 2.1 · Command A+ · Inkling Small · Muse Glimmer 30B · Nemotron 3 Nano 30B-A3B · Nemotron 3 Super 120B-A12B · Nemotron 3 Ultra 550B-A55B · Mamba-Codestral 7B · Nemotron 3.5 Super VL 120B-A12B · Nemotron 3.5 Bolt 74B-A9B · MiniMax M3.1 Flash · MiniMax M3 · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · Atria Dawn · Hydrogen-1.0 · Atria Dawn Preview · Hy4 Preview · K-EXAONE 2.0 750B-A37B · Inkling · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · ERNIE 5.5 Flash Base · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Muse Spark Open · Beam 1.0 501B-A23B · Kimi K3 · Mistral Large 4 · Mistral Large 3 · Mistral Small 4 119B · Leanstral 1.5 119B-A6B · Mixtral 8x22B · Qwen3-Coder-Next 80B-A3B · Qwen3-Coder 30B-A3B · Qwen3-Coder 480B-A35B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Intern S2 397B · Clef · Clef Flash · d1 3B · Humanizer · JEV 27B VL · Mellum2.1 12B-A2.5B · LightOnOCR-3 4B · Spark-X2.5 4B · Agnes-3.0-Qwen · Youtu-Parsing-Omni · Agnes-3.0-Flash · Mistral 7B v0.3 · Mistral Small 3.1 24B · Mistral Nemo · Ministral 8B · DeepSeek V3 · DeepSeek R1 Qwen3 8B · DeepSeek R1 Distill Qwen 32B · DeepSeek V3.1 · DeepSeek R1 Distill Qwen 14B · DeepSeek R1 Distill Qwen 7B · DeepSeek R1 Distill Llama 8B · Qwen3 4B · Qwen3 8B · Qwen2.5 7B · Qwen3 14B · Qwen2.5 3B · Qwen3.6 27B · Qwen3.5 27B · Qwen2.5-Coder 7B · Qwen2.5 32B · Qwen2.5-Coder 14B · Qwen3.5 35B-A3B · Qwen3 30B-A3B · Qwen2.5 14B · Qwen2.5-Coder 32B · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen2.5-Coder 3B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · Gemma 4 E4B · Gemma 4 E2B · Nemotron 3 Nano 4B · Nemotron 3.5 Lightning 30B-A3B · MiniCPM-V-4.7 35B-A3B · LFM2.5 24B-A2B · GLM-4.7 · Qwen3-VL 8B · Qwen2.5-VL 7B · Qwen3-VL 4B · Qwen2.5-VL 3B · Qwen2.5-VL 32B · Qwen2-VL 7B · GLM-4.5-Air · GLM-4.5 · phi-4 · Phi-3.5-mini · Phi-4-mini · Phi-3-mini-128k · Ling-3.1-flash · Step 5 Preview · Hy3 · Ornith-1.5 122B · Spark-X2.6 4B · Sage-A1.5 · MLExpert · Agents-A1 4B · Ling-3.0-flash-Sante · MiniCPM-OCR-1.0 · WeVisOne-VL 4B · Granite 4.1 3B · Qwen3-VL 30B-A3B · Mage-VL-Cowork · Spark-X2.6 1.7B · Qwen3.5 4B-Qwenputer · Kimi K3.1 Pro · 6.8-Code2Video · Qwen3.5 4B-GLB-3D-Coder · DeepSeek V3.2 · GLM-4.7-Flash · Laguna M.1 · Laguna XS.2 · Qwen3-VL 235B-A22B · Qwen2 7B · Qwen2.5 72B · Qwen3-VL 32B · Qwen2.5 14B-1M · Qwen3-Next 80B-A3B · Qwen2.5-VL 72B · Nemotron Nano 9B v2
Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.