HARDWARE BENCHMARK & VRAM ENVELOPE โข CONSUMER GPU24 GB VRAM โข 960 GB/s
What Models Can Run on AMD Radeon RX 7900 XTX (24GB GDDR6)?
24 GB VRAM960 GB/s Bandwidth355W TDPMSRP: $899Cloud: $0.35/hr on Vast.ai
AMD Radeon RX 7900 XTX (24GB GDDR6) provides 24 GB of usable memory with 960 GB/s memory bandwidth at 355W TDP. Cheapest 24GB brand-new GPU for ROCm / Ollama on Linux.
โก TIGHT FIT21.93 GB (91%)~32 t/s
Qwen 3.8 27B Instruct on AMD Radeon RX 7900 XTX (24GB GDDR6)
โก Tight Fit โ Runs 100% on GPU (Low Headroom)
โก TIGHT FIT
Required VRAM
21.93 GB
91% of hardware capacity (24 GB)Est. Decode Speed
~32 tok/s
Dense model @ 960 GB/sAvailable Headroom
+2.07 GB
Safe for OS display & full contextMemory Allocation & Headroom
21.93 GB allocated of 24 GB capacity
91% utilized
Weights: 16.32 GB
KV: (32K): 4.29 GB
Overhead: 1.32 GB
Free Headroom: +2.07 GB
โก Architecture & Throughput Transparency: Single-user decode speed (~32 tok/s) is memory-bandwidth bound at batch size = 1 on AMD Radeon RX 7900 XTX (24GB GDDR6) (960 GB/s). Prompt prefill / TTFT (~464 tok/s) is compute-bound and utilizes GPU Tensor cores. Actual latency varies with FlashAttention-2 and runtime engine (Ollama/vLLM/llama.cpp).
OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 ollama run qwen3.8:27bCloud Instance Options for Qwen 3.8 27B Instruct
On-DemandDeploy this model on an on-demand cloud GPU without local hardware constraints or power usage:
RunPod Cloud GPUsBest 1-Click Ollama & vLLM
$0.34/hr (RTX 4070 Ti) โ $2.39/hr (H100)Vast.ai GPU MarketplaceCheapest Dual RTX 3090 / 4090
$0.18/hr (RTX 3060) โ $0.55/hr (RTX 4090)Lambda GPU CloudEnterprise 8x H100 Clusters
$1.99/hr (GH200 / H100)Quantization Precision Matrix
32K ctx โข KV: Q8_0| Quantization | Weights | KV Cache | Total VRAM | Est. Speed | Fit Status |
|---|---|---|---|---|---|
| FP1616 bpw | 54.4 GB | 4.29 GB | 61.34 GB (256%) | 0 t/s | OOM |
| Q8_08.5 bpw | 28.83 GB | 4.29 GB | 34.88 GB (145%) | 0 t/s | OOM |
| Q6_K6.56 bpw | 22.3 GB | 4.29 GB | 28.12 GB (117%) | ~5 t/s | PARTIAL |
| Q5_K_M5.68 bpw | 19.31 GB | 4.29 GB | 25.03 GB (104%) | ~6 t/s | PARTIAL |
| Q4_K_M4.8 bpw | 16.32 GB | 4.29 GB | 21.93 GB (91%) | ~32 t/s | FITS |
| FP44.25 bpw | 14.42 GB | 4.29 GB | 19.96 GB (83%) | ~36 t/s | FITS |
| IQ3_XS3.3 bpw | 11.15 GB | 4.29 GB | 16.58 GB (69%) | ~46 t/s | FITS |
Export Full Architecture & Infrastructure Spec
Get an executive-ready PDF report with exact memory math, hardware benchmarks, and cost comparisons.
All Open-Weights Models Tested on AMD Radeon RX 7900 XTX (24GB GDDR6) (Q4_K_M @ 32K Context)
Standard Q4_K_M precision with 32K context window and Q8_0 KV cache
| Model | Architecture | Total VRAM Needed | Headroom | Est. Decode Speed | Compatibility | Detailed Config |
|---|---|---|---|---|---|---|
| Qwen 3.8 27B Instruct Alibaba Cloud | 27.2B Dense | 21.93 GB(91%) | +2.07 GB | ~32 tok/s | โก TIGHT FIT | Configure CLI โ |
| Qwen 3.6 35B-A3B MoE Alibaba Cloud | 35B MoE | 24.1 GB(100%) | -0.1 GB | ~56 tok/s | โก PARTIAL | Configure CLI โ |
| DeepSeek-V4.1-Flash (552B Engram MoE) DeepSeek | 552B MoE | 345.59 GB(1440%) | -321.59 GB | 0 (OOM) | โ OOM | Configure CLI โ |
| Meta Muse Spark Open (816B-A42B MoE) Meta AI | 816B MoE | 512.86 GB(2137%) | -488.86 GB | 0 (OOM) | โ OOM | Configure CLI โ |
| Google Gemma 4 26B MoE Google | 26.4B MoE | 20.23 GB(84%) | +3.77 GB | ~169 tok/s | โ FITS | Configure CLI โ |
| Google Gemma 4 E4B (Edge 4B) Google | 4.1B Dense | 4.24 GB(18%) | +19.76 GB | ~207 tok/s | โ FITS | Configure CLI โ |
| DeepSeek-R1 Distill Qwen 32B DeepSeek | 32.8B Dense | 25.41 GB(106%) | -1.41 GB | ~6 tok/s | โก PARTIAL | Configure CLI โ |
| DeepSeek-R1 Distill Qwen 14B DeepSeek | 14.8B Dense | 13.16 GB(55%) | +10.84 GB | ~57 tok/s | โ FITS | Configure CLI โ |
| Meta Llama 4 Scout (109B-A17B MoE) Meta AI | 109B MoE | 71.66 GB(299%) | -47.66 GB | 0 (OOM) | โ OOM | Configure CLI โ |
| Meta Llama 3.3 70B Instruct Meta AI | 70.6B Dense | 49.96 GB(208%) | -25.96 GB | 0 (OOM) | โ OOM | Configure CLI โ |
| Meta Llama 3.1 8B Instruct Meta AI | 8B Dense | 7.87 GB(33%) | +16.13 GB | ~104 tok/s | โ FITS | Configure CLI โ |
| Microsoft Phi-4 Mini 3.8B Microsoft | 3.8B Dense | 3.92 GB(16%) | +20.08 GB | ~224 tok/s | โ FITS | Configure CLI โ |
| Qwen 2.5 Coder 32B Instruct Alibaba Cloud | 32.5B Dense | 25.22 GB(105%) | -1.22 GB | ~6 tok/s | โก PARTIAL | Configure CLI โ |
| DeepSeek Coder V2 236B MoE DeepSeek | 236B MoE | 151.34 GB(631%) | -127.34 GB | 0 (OOM) | โ OOM | Configure CLI โ |
| Meta Llama 3.1 405B Instruct Meta AI | 405B Dense | 260.72 GB(1086%) | -236.72 GB | 0 (OOM) | โ OOM | Configure CLI โ |
| Mistral Large 2 (123B Instruct) Mistral AI | 123B Dense | 83.04 GB(346%) | -59.04 GB | 0 (OOM) | โ OOM | Configure CLI โ |
| Google Gemma 2 27B Instruct Google | 27.2B Dense | 23.81 GB(99%) | +0.19 GB | ~32 tok/s | โก TIGHT FIT | Configure CLI โ |
| Google Gemma 2 9B Instruct Google | 9.2B Dense | 12.1 GB(50%) | +11.9 GB | ~85 tok/s | โ FITS | Configure CLI โ |