llamaperf

AMD Radeon 780M

AMD · shared memory · 8 reports

On the AMD Radeon 780M, Qwen3.6 35B · 3B active at 8-bit, the model most run on it, generates a median of 19.7 tokens per second from 2 plain runs (community reports, as of 22 Nov 2026).

As of 22 Nov 2026, the models most run on the AMD Radeon 780M, each one size at one quant level, with the median generation speed of its plain runs (one device, one request, no speculative decoding):

Bars are medians on one scale, 0 to 25.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Engines people use on it: llama.cpp 6 (reports) · Ollama 1 (reports)

Run models on your AMD Radeon 780M? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Reported performance on the AMD Radeon 780M

These reports mix GPU counts and memory setups, so a model listed here may have needed extra cards or CPU offloading. It has no memory of its own and borrows the machine's RAM, so how large a model fits depends on the machine, and the calculator does not size it. Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

Unknown family 26B (4B active)

AMD Radeon 780M · llama.cpp · 16,384 ctx

Tone: mixedAMD hardware
generation:
25.0 tokens/s
quant:
Q4 QAT (GGUF)
flash attention:
on
agenticlong-context

User reports a fully local Italian voice assistant on a mini PC with a Radeon 780M iGPU and 64GB DDR5 shared memory, reaching a median ~2.2s from end of speech to first audio. The LLM is a 26B-A4B MoE at Q4 QAT running in llama.cpp on Vulkan at ~25 tok/s, with 16k context, one slot, flash attention and cache reuse. Prefill of the turn costs ~1.0s (~0.35s fixed per request plus ~3ms/token), ASR ~0.75s and first sentence plus TTS first chunk ~0.55s. The user puts the calculated floor on this box at ~1.2-1.5s. Smaller dense models were benchmarked and rejected for factual fidelity, and KV-cache warming during speech was net neutral-to-negative on one slot. The user asks what else could be done before buying a 24GB dGPU.

Nov 16, 2026
Tone: positiveAMD hardware
generation:
37.0 tokens/s
agentictool-use

User reports LFM2.5-24B-A2B at about 37 t/s at zero context on an AMD Radeon 780M iGPU. No engine, quant or context settings are stated beyond the GGUF build linked. User says it is not a coding model but a task executor, and that it pairs well with Hermes for handing off low-to-mid complexity tasks.

Nov 15, 2026

Qwen3.8 27B

AMD Radeon 780M · llama.cpp · 32,768 ctx

Tone: mixedAMD hardware
prompt processing (prefill):
74.0 tokens/s
quant:
IQ3_S (GGUF)
kv:
q8_0
codingmultilingual

User reports Qwen3.8-27B at 5.1-8.3 t/s generation and ~74 t/s prompt on a Radeon 780M laptop with 32GB unified RAM. Setup is llama.cpp with IQ3_S quant, q8_0 KV cache, 32768 context, and DFlash2 speculative decoding. User also ran Gemma 4 26B-A4B Q4_K_M at 21.8-25.8 t/s, Qwen3.6-35B-A3B IQ4_XS at 24.4-33.3 t/s, and LFM2.5-24B-A2B Q4_0 at 38.7-40.3 t/s. User plans to use Qwen3.8-27B for coding and Gemma 4 26B-A4B for other tasks.

Oct 14, 2026
Tone: positiveAMD hardware
generation:
25.0 tokens/s
prompt processing (prefill):
208.7 tokens/s
quant:
Q4_K_M (GGUF)

User reports Gemma4 26B Q4_K_M at ~25.00 t/s generation and ~208.72 t/s prompt processing on an AMD Radeon 780M iGPU. Setup is llama.cpp with Vulkan backend, Q4_K_M GGUF, -ngl 99, on a MINISFORUM UM890 Pro mini PC running Ubuntu 24.04. A CLI smoke test gave ~23.4 t/s generation and ~37.3 t/s prompt; a no-reasoning run gave ~24.4 t/s generation and ~117.6 t/s prompt. Ollama on the same box was around 4.5 t/s generation, roughly a 5x-6x uplift. Ollama's installed Gemma4 blob could not be loaded directly in upstream llama.cpp due to a tensor count mismatch.

Sep 26, 2026
Tone: mixedAMD hardware
generation:
3.2 tokens/s
prompt processing (prefill):
32.5 tokens/s
coding

User reports Qwen3.8 27B at 3.20 t/s generation and 32.45 t/s prompt processing on a Ryzen 9 7940HS with Radeon 780M iGPU and 24GB RAM. Setup is Ollama on two machines: a Minisforum UM790 Pro and a home build with the same Ryzen 9 7940HS, both with 24GB RAM. The Minisforum run reached 4.73 t/s generation and 20.52 t/s prompt processing. Both runs stopped mid-task and follow-up prompts returned no output. User expected low throughput but not the failures.

Sep 18, 2026
Tone: positiveAMD hardware
generation:
21.1 tokens/s
prompt processing (prefill):
287.3 tokens/s
quant:
Q8_0
kv:
q8_0

User benchmarks Qwen3.6 35B-A3B Q8_0 on a Ryzen 7 260 with a 780M iGPU and 64 GB DDR5, reaching pp8192 287.33 t/s and tg128 21.06 t/s. Setup is the Vulkan backend. Gemma 4 31B Q8_0 on the same hardware gives pp8192 51.59 t/s and tg128 2.46 t/s. With MTP, Gemma 4 31B reaches tg ~5.76 t/s, and Qwen3.6 35B-A3B with MTP and partial offloading reaches tg ~34.85 t/s. The user mentions an RTX 5060 8GB as a bonus for MoE partial offloading.

Sep 7, 2026
AMD hardware
generation:
18.4 tokens/s
prompt processing (prefill):
311.4 tokens/s
quant:
Q8 (GGUF)
kv:
Q8

User benchmarks ROCm against Vulkan on a Radeon 780m iGPU. ROCm gives a 50% pp speedup for dense models. The user also reports Qwen3.8 27B results.

Sep 7, 2026
Tone: mixedAMD hardware
prompt processing (prefill):
100.0 tokens/s

User reports ROCm 7.14 on a Radeon 780M with llama.cpp is fast but unstable and crashes. Setting AMD_SERIALIZE_KERNEL=3 stabilizes it but drops prompt processing to about 100 t/s, down from 200-300 t/s without the workaround. User asks for advice.

Sep 7, 2026

Get a weekly email of new AMD Radeon 780M reports and newly released models that fit it.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardwareQuant / engineReported contextGeneration
Unknown family 26B (4B active)
AMD Radeon 780M
Q4 QAT
llama.cpp
16,38425.0 tokens/s
LFM2.5 24B (2.45B active) A2.5B
AMD Radeon 780M
Not reported
Engine not reported
Not reported37.0 tokens/s
Gemma 4 26B (4B active)
AMD Radeon 780M
Q4_K_M
llama.cpp
Not reported25.0 tokens/s
Qwen3.8 27B
2× AMD Radeon 780M
Not reported
Ollama
Not reported3.2 tokens/s
Qwen3.6 35B (3B active)
AMD Radeon 780M
Q8_0
llama.cpp
Not reported21.1 tokens/s
Qwen3.6 35B (3B active)
AMD Radeon 780M
Q8
llama.cpp
Not reported18.4 tokens/s

Frequently asked

How fast is the AMD Radeon 780M for local LLMs?

On the AMD Radeon 780M, Qwen3.6 35B · 3B active at 8-bit, the model most run on it, generates a median of 19.7 tokens per second from 2 plain runs (community reports, as of 22 Nov 2026). Also reported: Gemma 4 26B · 4B active at 4-bit (25.0 t/s, one plain run).