VOOZH about

URL: https://willitrunai.com/can-run/hf-nousresearch--hermes-4-3-36b-gguf-on-rx-6800-xt-16gb

⇱ Hermes 4.3 36B on RX 6800 XT 16GB? No — Alternatives

Can Hermes 4.3 36B run on RX 6800 XT 16GB?

NO — Won't Fit

F0Won't run
○Estimated from fit model

Hermes 4.3 36B needs ~28.7 GB but RX 6800 XT 16GB only has 16.0 GB. Try a smaller quantization or lighter model.

Runtime: llama.cppCapacity: No fitBandwidth: MediumStack: StandardBottleneck: Memory capacity
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 28.7 GB, exceeds 16.0 GB available
28.7 GB required16.0 GB available
179% VRAM needed

12.7 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.9 tok/s

TTFT

67532 ms

Safe context

4K

Memory

28.7 GB / 16.0 GB

Offload

40%

Memory breakdown

Weights22.0 GB
KV Cache4.2 GB
Runtime0.9 GB
Headroom1.6 GB

See how fast it feels

With memory offload — actual speed may be lower
See how fast it feelsHermes 4.3 36B on RX 6800 XT 16GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step. Given information: - Speed = 60 mph (miles per hour) - Time = 2.5 hours Formula: Distance = Speed x Time Calculation: Distance = 60 mph x 2.5 h = 150 miles The train travels 150 miles. Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time. Breakdown: - First half: 1.25 hours at 60 mph = 75 miles - Stop: 20 minutes (no distance) - Second half: 1.25 hours at 60 mph = 75 miles Total distance: 150 miles (same) Total time: 2.5 h + 0.33 h = 2.83 hours Average speed: 150 / 2.83 = 53 mph The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 2.9 tok/s decode · 67.5s TTFT (warm) · 7 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 28.7 GB, but this setup only exposes 16.0 GB of usable VRAM.

Best improvement path

Add more VRAM headroom

The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatFToo heavy3.4 tok/s31364 ms4K
CodingFToo heavy2.9 tok/s67532 ms4K
Agentic CodingFToo heavy2.1 tok/s131130 ms4K
ReasoningFToo heavy2.9 tok/s79811 ms4K
RAGFToo heavy2.1 tok/s163912 ms4K

Quantization options

How Hermes 4.3 36B (36B params) fits at each quantization level on RX 6800 XT 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
14.0 GB
LowF0
Q3_K_S
3
17.6 GB
LowF0
NVFP4
4
20.2 GB
MediumF0
Q4_K_M
4
22.0 GB
MediumF0
Q5_K_M
5
25.9 GB
HighF0
Q6_K
6
29.5 GB
HighF0
Q8_0
8
38.5 GB
Very HighF0
F16
16
73.8 GB
MaximumF0

Upgrade options

Hardware that runs Hermes 4.3 36B well

Radeon AI PRO R9700 32GBBudget pick
32 GB VRAM (+16)640 GB/s (+128)
C
Makes the model fit on the accelerator instead of staying completely out of reach.17.2 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$1,899 MSRP

Radeon Pro W6800 32GBBest value
32 GB VRAM (+16)
C
Makes the model fit on the accelerator instead of staying completely out of reach.13.1 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$2,249 MSRP

Radeon Pro W7800 32GBAMD upgrade
32 GB VRAM (+16)576 GB/s (+64)
C
Makes the model fit on the accelerator instead of staying completely out of reach.15.5 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$2,499 MSRP

👁 NVIDIA
NVIDIA A100 40GBBiggest leap
40 GB VRAM (+24)1555 GB/s (+1043)
B
Makes the model fit on the accelerator instead of staying completely out of reach.59.5 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$10,000 MSRP

Frequently asked questions

See all results for RX 6800 XT 16GBSee all hardware for Hermes 4.3 36B