Can the AMD Radeon RX 7900 XT run Hemmingway-1?

Hemmingway-1 · AMD Radeon RX 7900 XT · 8,192 ctx · whole model residentQ4_K_M sizesize rangeSpeedestimate

IT FITS

Yes. 4 of 9 formats evaluated fit in 20 GB, at 8,192 tokens. No published file exists for this pair, so every size is rebuilt from the pinned architecture. The best quality that fits is Q4_K_M, needing 18.0 GB and running at an estimated 42 tokens per second.

Fitting in memory is not the same as loading. Whether the runtime and version you have supports this architecture and format on this machine has not been tested here.

Find the AMD Radeon RX 7900 XT: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.

4/9formats that fit

20 GBdevice memory

18.0 GBneeded at best quality

~42tokens per second, estimatedFaster than you read

800GB/s bandwidth

How long a conversation. At Q4_K_M, this pair holds 38,610 tokens of context — roughly 28,958 words — needing 20.0 GB. Past that the AMD Radeon RX 7900 XT runs out of memory, not the model out of context, which would allow 262,144. This is the wall a long chat hits after it has already loaded fine. The nearest round setting below it is 32,768.

Every format evaluated

No published file exists for this pair, so every size is rebuilt from the pinned architecture. The Basis column says which is which for each row. Decode and first-token figures are calibrated estimates, not runs on this card.

Format	Needs	Of 20 GB	Fits	Decode	First token	Basis
FP16	55.3 GB	277%	short by 35.3 GB	does not run	—	size range
Q8_0	30.1 GB	150%	short by 10.1 GB	does not run	—	size range
Q6_K	23.6 GB	118%	short by 3.58 GB	does not run	—	size range
Q5_K_M	20.7 GB	104%	short by 0.71 GB	does not run	—	size range
Q5_0	20.3 GB	101%	short by 0.27 GB	does not run	—	size range
Q4_K_M	18.0 GB	90%	yes	~42 tok/s	no comparable peak	size range
Q4_0	17.1 GB	86%	yes	~44 tok/s	no comparable peak	size range
Q3_K_M	14.9 GB	75%	yes	~51 tok/s	no comparable peak	size range
Q2_K	12.1 GB	61%	yes	~65 tok/s	no comparable peak	size range

Sized at 8,192 tokens of context with the whole model resident — weights, the KV cache and the runtime reserve, offload off. Speed is only quoted for a format that fits: a rate for a configuration that cannot load is not a fact about anything.

Why the first-token figure is the same on every row

First token is modelled from the arithmetic the prompt requires, and that count does not change with the weight format — which is why it reads the same on every row. Real prefill does vary by format, because a quantized matmul is a different kernel; this model does not capture that, and the figure should be read as an order of magnitude rather than a ranking between formats.

What the labels mean

published data: Read from a published source — a file's byte count, a model's configuration or a manufacturer's specification — or exact arithmetic on such values. Not a measurement on a machine.
reconstructed size: Weight size reconstructed from the pinned architecture, because no published file exists.
size range: Only a lower and an upper bound are claimed for this weight size.
estimate: Calculated from sourced inputs by a stated method; an estimate, not a measurement.

Change anything

This page fixes the context at 8,192 tokens and one device. Batch, concurrent users, KV-cache format, clusters and rental cost are all in the calculator, already set to this pairing.

Open in the calculator →Everything the AMD Radeon RX 7900 XT runs Best models for 20 GB

Where these numbers come from

Hemmingway-1’s architecture is read from its publisher’s own config.json at a pinned revision, and the AMD Radeon RX 7900 XT’s 20 GB and 800 GB/s come from the manufacturer’s specification. How far each figure can be trusted is published, per format and worst case included, on the accuracy scorecard.

Building this into your own product? A free API key returns exactly these figures, and the widget puts this answer on a product page with one script tag.

Use this answer in your own product

As JSON, from the API

curl -s https://llmbottleneck.com/v1/analyze \
  -H "Authorization: Bearer $LLMB_KEY" -H "content-type: application/json" \
  -d '{"model":"altworld-hemmingway-1","quantization":"Q4_K_M","context":8192,"hardware":"amd-radeon-rx-7900-xt"}'

Same engine, same evidence, every field sourced. Free key in one step →

On your page, as a widget

<script src="https://llmbottleneck.com/widget.js"
  data-model="altworld-hemmingway-1" data-quantization="Q4_K_M"
  data-hardware="amd-radeon-rx-7900-xt" data-context="8192"></script>

No key needed. Unbranded, with your own buy button, on Pro and Business →