Yes — with 29.7 GB to spare

DeepSeek V4 Flash 284B-A13B at Q4_K_M fits your Instinct MI300X entirely on the GPU at 8K context, at an estimated 169 tokens per second. Past 637K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully on GPU 8K context Q4_K_M · 159.7 GB MIT Released 31 Jul 2026 Not in the Ollama library

The V4 for 192–256 GB machines: Q3 squeezes into 192 GB, Q4 wants 256 GB, and 128 GB falls short even at Q2. Cache is modelled as a 576-wide latent; V4 compresses it further at long context, so this is conservative.

Hardware requirements What hardware do I need to run DeepSeek V4 Flash 284B-A13B? →

At Q4_K_M with an 8K context: a 192 GB GPU (Instinct MI300X) or a 256 GB Mac (M3 Ultra). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 159.7 GB
Weights 159.7 GB KV cache @ 8K 0.38 GB Runtime overhead 0.6 GB Free 29.7 GB of 190.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 281.0 GB 282.0 GB — ~3.3 −0.1% ppl 91.6 GB over
Q6_K 216.9 GB 217.9 GB — ~10 −0.4% ppl 27.5 GB over
Q5_K_M 187.5 GB 188.4 GB 49K 144 −0.8% ppl Long context
Q4_K_M 159.7 GB 160.7 GB 637K 169 −1.9% ppl Recommended
Q3_K_M 129.3 GB 130.3 GB 1024K 209 −5.4% ppl Long context
Q2_K 110.8 GB 111.7 GB 1024K 243 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.

How to run it

terminal
$ llama-server \
    -hf deepseek-ai/DeepSeek-V4-Flash-0731:Q4_K_M \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 159.7 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to 637K context on this card.
See all models for this rig Compare with another model

Related models on an Instinct MI300X

ModelTotalTok/s est.
DeepSeek V4.1 Flash 552B-A16B
552B MoE · same family
Q4_K_M · 311.0 GB — Won't fit
DeepSeek V4 Pro 1.6T-A49B
1650B MoE · same family
Q4_K_M · 928.9 GB — Won't fit
GLM-5.3-Flash 320B-A18B
321B MoE · similar size
Q4_K_M · 181.2 GB 122 Tight fit
Qwen3 235B-A22B
235B MoE · similar size
Q4_K_M · 134.2 GB 100 Runs great
Ornith 1.5 397B-A17B
397B MoE · similar size
Q4_K_M · 224.1 GB — Won't fit
Qwen3.5 397B-A17B
403B MoE · similar size
Q4_K_M · 227.4 GB — Won't fit
Qwen3.8-Flash-Next 180B-A6B
180B MoE · similar size
Q4_K_M · 102.0 GB 366 Runs great

Every model against the Instinct MI300X →

DeepSeek V4 Flash 284B-A13B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
160.7 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
160.7 GB — Won't fit
M4 · 16 GB
10.7 GB usable · 120 GB/s
160.7 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
160.7 GB — Won't fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
160.7 GB — Won't fit
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
160.7 GB — Won't fit
M3 Ultra · 256 GB
192.0 GB usable · 800 GB/s
160.7 GB 29 Runs great

All 114 devices, by tier →